© 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. 30158
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    GP
    -0.28
    .OPEN
    -0.28
    osing
    -0.27
    éĵ¢
    -0.26
     provision
    -0.25
    ooting
    -0.25
    好çİ©
    -0.24
    ti
    -0.24
    onden
    -0.24
    hou
    -0.23
    POSITIVE LOGITS
    dia
    0.28
     corrid
    0.28
    umatic
    0.27
    afc
    0.26
     contradictions
    0.26
    åİŁåŀĭ
    0.26
    åĩºèĩª
    0.25
    orst
    0.25
     bow
    0.24
    ä¼ļ对
    0.23
    Activations Density 2.454%

    No Known Activations