© 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. 62456
    Prev
    Next
    INDEX
    Explanations

    .jar

    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
     tact
    -0.07
    闪电
    -0.07
    ὗ
    -0.07
     dụ
    -0.07
    agnost
    -0.07
    .fx
    -0.07
    RACT
    -0.07
    _charge
    -0.07
    transpose
    -0.07
     ListTile
    -0.07
    POSITIVE LOGITS
     band
    0.06
    ке
    0.06
    Despite
    0.06
    Descripcion
    0.06
    )//
    0.06
     office
    0.06
     dollars
    0.06
    ではない
    0.06
     oleh
    0.06
    ///↵↵
    0.06
    Activations Density 0.001%

    No Known Activations