© 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. 9-TRANSCODER-HP
    7. 30196
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    house
    -0.28
    houses
    -0.25
     div
    -0.25
     ham
    -0.25
    l
    -0.25
    tag
    -0.24
    [h
    -0.24
    oscope
    -0.24
    [P
    -0.24
    à¹ģฮ
    -0.24
    POSITIVE LOGITS
    weeney
    0.26
    丰满
    0.26
    unset
    0.25
    vey
    0.25
     sæ
    0.25
     tablespoons
    0.24
    éĢ»
    0.24
    ç¥ĵ
    0.24
    ully
    0.23
     Mixing
    0.23
    Activations Density 3.782%

    No Known Activations