© 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. 9730
    Prev
    Next
    INDEX
    Explanations

    Species names

    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
    大师
    -0.07
     שהיו
    -0.07
    emax
    -0.06
     mö
    -0.06
    _InternalArray
    -0.06
    有两种
    -0.06
    诞生
    -0.06
    .Raycast
    -0.06
     seemed
    -0.06
    申花
    -0.06
    POSITIVE LOGITS
    >(),
    0.08
    CLASS
    0.07
    Single
    0.07
     primal
    0.07
     Geometry
    0.07
    (transaction
    0.07
    _pay
    0.07
    ateral
    0.07
    'We
    0.07
    (Location
    0.07
    Activations Density 0.068%

    No Known Activations