© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 49957
    Prev
    Next
    INDEX
    Explanations

    how

    np_max-act · gemini-2.0-flash

    Instances of the interrogative "how" and related "how to" / instructional/question phrasing.

    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
     sendMessage
    -0.07
     البن
    -0.07
     sentinel
    -0.07
     conn
    -0.07
    支
    -0.07
     main
    -0.07
    党支部
    -0.07
     xưa
    -0.07
    沨
    -0.06
     visceral
    -0.06
    POSITIVE LOGITS
     how
    0.09
     Expanded
    0.07
    _ATTRIBUTES
    0.07
    㮾
    0.07
     the
    0.07
    expand
    0.07
    	lua
    0.07
     LOCATION
    0.06
    研究报告
    0.06
     HRESULT
    0.06
    Activations Density 0.168%

    No Known Activations