© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29752
    Prev
    Next
    INDEX
    Explanations

    and

    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
     sav
    -0.30
     discipline
    -0.29
    åİĭ
    -0.29
    央
    -0.27
     bay
    -0.27
     Save
    -0.27
    责任
    -0.26
    bay
    -0.26
    主管éĥ¨éŨ
    -0.25
    ,Th
    -0.25
    POSITIVE LOGITS
    shortcode
    0.26
    åijĬè¯īä½ł
    0.25
    ä¸įå®ļ
    0.25
    RAP
    0.25
    arah
    0.25
    éľĩæĴ¼
    0.23
    KHR
    0.23
    .%
    0.23
     Shorts
    0.23
    ading
    0.23
    Activations Density 44.543%

    No Known Activations