© 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. 19926
    Prev
    Next
    INDEX
    Explanations

    Mixed topics and genres

    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
    ä¸įèĪį
    -0.28
    (interface
    -0.27
    好çļĦ
    -0.26
    è´ı
    -0.25
    è¿ĩ
    -0.25
    ç¬Ķ
    -0.25
    owan
    -0.25
    -0.25
    ffects
    -0.25
    yor
    -0.25
    POSITIVE LOGITS
    èĤ
    0.25
     jokes
    0.25
    *>(&
    0.25
    _DEVICE
    0.24
    ERING
    0.24
     mé
    0.24
     repos
    0.24
    èĤĥ
    0.24
    .factory
    0.23
    :red
    0.23
    Activations Density 2.609%

    No Known Activations