© 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. 29374
    Prev
    Next
    INDEX
    Explanations

    form

    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
    ç«ĻçĿĢ
    -0.35
    屿
    -0.29
    票
    -0.27
     exploded
    -0.26
     konk
    -0.25
    .gov
    -0.25
     net
    -0.24
    æ¥Ĥ
    -0.24
    å®ļäºĨ
    -0.24
     opr
    -0.24
    POSITIVE LOGITS
    å±Ĥåĩº
    0.28
    åİ¿å§Ķ书记
    0.25
    æĦı大
    0.25
    _LEAVE
    0.25
    osaur
    0.25
    ategy
    0.24
     kHz
    0.24
    rão
    0.24
     Lodge
    0.24
    ensi
    0.24
    Activations Density 0.895%

    No Known Activations