© 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. 100039
    Prev
    Next
    INDEX
    Explanations

    IT

    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
    升温
    -0.07
     האחרונות
    -0.07
     לד
    -0.07
    Loc
    -0.06
     signIn
    -0.06
     Auf
    -0.06
    壽
    -0.06
     sobie
    -0.06
    ております
    -0.06
    _sec
    -0.06
    POSITIVE LOGITS
     Partial
    0.07
    NONE
    0.07
    벌
    0.07
    ArrayType
    0.07
     partners
    0.07
    .items
    0.06
    调皮
    0.06
     throwing
    0.06
    Patrick
    0.06
    (FLAGS
    0.06
    Activations Density 0.001%

    No Known Activations