© 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. 71611
    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
    蔹
    -0.07
     <%=
    -0.07
     omp
    -0.07
    .Categories
    -0.07
    kp
    -0.07
    刑侦
    -0.07
    Weapons
    -0.07
    PropertyChanged
    -0.07
    .capacity
    -0.07
     stringstream
    -0.07
    POSITIVE LOGITS
    .neg
    0.08
    sic
    0.07
    ren
    0.07
    _lazy
    0.07
    Render
    0.06
     cif
    0.06
    北京
    0.06
    sız
    0.06
    厭
    0.06
    )x
    0.06
    Activations Density 0.011%

    No Known Activations