© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 7-RESID-POST-AA
    11. 59749
    Prev
    Next
    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IRA
    -0.07
     Kelly
    -0.07
     detr
    -0.07
    (args
    -0.06
     luaL
    -0.06
     unravel
    -0.06
    三千
    -0.06
    纵深
    -0.06
     dile
    -0.06
    HUD
    -0.06
    POSITIVE LOGITS
    +
    0.12
    ,user
    0.09
    (face
    0.08
    $username
    0.07
    versible
    0.07
    .setPositiveButton
    0.07
    ¸
    0.07
    .toolbox
    0.07
    .pool
    0.07
    peace
    0.07
    Activations Density 0.031%

    No Known Activations