© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 5350
    Prev
    Next
    INDEX
    Explanations

    data breaches credit monitoring

    np_max-act · gemini-2.0-flash

    sentences or phrases describing legal/regulatory breach-notification requirements — who must notify, timing (e.g., within X hours/days), and what information/steps to provide to affected individuals or authorities.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    פעילות
    -0.07
    (App
    -0.07
    isha
    -0.07
     ofs
    -0.07
    怄
    -0.07
    بيب
    -0.07
     minlength
    -0.07
    组织生活
    -0.07
     Quaternion
    -0.07
     lập
    -0.07
    POSITIVE LOGITS
    เคร
    0.07
    utting
    0.07
    时限
    0.06
    𝐞
    0.06
    	q
    0.06
    ------------------------------------------------------------------------------------------------
    0.06
    extract
    0.06
     Within
    0.06
    命令
    0.06
    눚
    0.06
    Activations Density 0.012%

    No Known Activations