© 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. 19-RESID-POST-AA
    11. 46988
    Prev
    Next
    INDEX
    Explanations

    .Assert or .Assertions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     أصبح
    -0.07
     Fax
    -0.07
     sử
    -0.07
    ��
    -0.06
     otp
    -0.06
     áp
    -0.06
    olf
    -0.06
    .env
    -0.06
    elsius
    -0.06
     advertis
    -0.06
    POSITIVE LOGITS
    如有侵权
    0.07
    _working
    0.07
     المج
    0.07
     CRA
    0.07
    GameData
    0.07
    是你
    0.07
     NETWORK
    0.06
    -create
    0.06
    されること
    0.06
    蚶
    0.06
    Activations Density 0.001%

    No Known Activations