© 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. 15-RESID-POST-AA
    11. 55381
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ageing
    -0.08
    fre
    -0.07
     diseases
    -0.07
    ．
    -0.07
     colours
    -0.07
    展现
    -0.07
    tras
    -0.07
    穩定
    -0.06
    ль
    -0.06
    옯
    -0.06
    POSITIVE LOGITS
    sını
    0.07
     ort
    0.07
    🕣
    0.07
    読
    0.07
    (mutex
    0.07
     (?
    0.07
    öt
    0.06
     vå
    0.06
     Pocket
    0.06
    곳
    0.06
    Activations Density 0.001%

    No Known Activations