© 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. 111416
    Prev
    Next
    INDEX
    Explanations

    %

    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
    .like
    -0.09
     Come
    -0.08
    .people
    -0.07
    Авто
    -0.07
    草坪
    -0.07
    Cole
    -0.07
    כתב
    -0.07
     Reports
    -0.07
    fff
    -0.07
    .RESULT
    -0.07
    POSITIVE LOGITS
    不能再
    0.07
    Readable
    0.07
    /trunk
    0.07
    铕
    0.06
    ester
    0.06
     primaryKey
    0.06
     Rand
    0.06
    Develop
    0.06
     encoded
    0.06
     faint
    0.06
    Activations Density 0.000%

    No Known Activations