© 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. 81311
    Prev
    Next
    INDEX
    Explanations

    ma

    np_max-act · gemini-2.0-flash
    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
     toe
    -0.07
     met
    -0.07
     nos
    -0.06
     דו
    -0.06
    携
    -0.06
     numa
    -0.06
    imento
    -0.06
    technology
    -0.06
     wed
    -0.06
    datatype
    -0.06
    POSITIVE LOGITS
    药业
    0.07
    datasets
    0.07
     arbitrarily
    0.07
    BK
    0.07
    binary
    0.07
    跑去
    0.07
     Casual
    0.06
    游客
    0.06
    .standard
    0.06
    吃惊
    0.06
    Activations Density 0.001%

    No Known Activations