© 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. 29936
    Prev
    Next
    INDEX
    Explanations

    Scientific texts

    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
     Kamp
    -0.26
     Lump
    -0.25
     Alloy
    -0.25
    plib
    -0.25
     alloy
    -0.25
     Rec
    -0.24
    æ¿ĢåĬ¨
    -0.24
    aget
    -0.24
     Recycling
    -0.24
     rec
    -0.24
    POSITIVE LOGITS
    åĪĨéĴŁå·¦åı³
    0.28
    ies
    0.27
    å¨ĺå¨ĺ
    0.26
    ä¹ĭå¤ľ
    0.25
    (cors
    0.25
    ä¹ĭæĦı
    0.24
    readcrumb
    0.24
     комиÑģÑģи
    0.24
     Greater
    0.24
     greater
    0.23
    Activations Density 0.626%

    No Known Activations