© 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. 4235
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    first-person reporting of research methods or findings in scientific articles, especially marked by “we” statements and “The Study” section headers.

    oai_token-act-pair · gpt-5Triggered 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
     değiştir
    -0.07
    .answer
    -0.07
    income
    -0.07
    疍
    -0.07
    大切
    -0.07
    nano
    -0.06
    slashes
    -0.06
     çocuklar
    -0.06
    奪
    -0.06
     Calder
    -0.06
    POSITIVE LOGITS
     Moines
    0.07
    ็ด
    0.07
     pracy
    0.07
    ประจำ
    0.07
     лечения
    0.07
    局部
    0.07
    𝚝
    0.07
     seating
    0.06
    -CS
    0.06
     la
    0.06
    Activations Density 0.026%

    No Known Activations