© 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. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 17771
    Prev
    Next
    INDEX
    Explanations

    math collection problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     similarly
    -0.31
    åIJĮæł·
    -0.30
    缸åIJĮçļĦ
    -0.28
     term
    -0.26
    jin
    -0.25
    component
    -0.25
     guard
    -0.25
    缸åIJĮ
    -0.25
     ident
    -0.25
    .same
    -0.25
    POSITIVE LOGITS
    ç»ĻæĤ¨
    0.28
     base
    0.26
     heter
    0.25
     Loy
    0.25
    çĻ½äºij
    0.24
    Ahead
    0.24
    back
    0.24
    ueur
    0.23
    uencia
    0.23
    athy
    0.23
    Activations Density 0.906%

    No Known Activations