© 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. 24062
    Prev
    Next
    INDEX
    Explanations

    otherwise

    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
     porte
    -0.08
     topp
    -0.08
     ترك
    -0.07
    TemplateName
    -0.07
    パーティ
    -0.07
    (Level
    -0.07
     pack
    -0.06
     לוק
    -0.06
    rez
    -0.06
    mass
    -0.06
    POSITIVE LOGITS
    ⌋
    0.07
    .references
    0.07
    ┼
    0.06
    艉
    0.06
    agh
    0.06
    当时的
    0.06
    苁
    0.06
    [of
    0.06
     reject
    0.06
     /*!↵
    0.06
    Activations Density 0.000%

    No Known Activations