© 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. 30086
    Prev
    Next
    INDEX
    Explanations

    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
    enses
    -0.28
    oders
    -0.27
    éĶŃ
    -0.27
    åIJĮæŃ¥
    -0.25
    å¿į
    -0.24
    å¾Ĺå¾Ī
    -0.24
    buttons
    -0.24
    æŃ£åĵģ
    -0.23
    arus
    -0.23
    Buttons
    -0.23
    POSITIVE LOGITS
    æĸ½å·¥
    0.38
    设计
    0.35
    è¨Ńè¨Ī
    0.35
     дизайн
    0.31
    çļĦ设计
    0.31
    设计æĸ¹æ¡Ī
    0.30
    楼çĽĺ
    0.30
    设计çIJĨ念
    0.30
     design
    0.30
    建çŃij设计
    0.30
    Activations Density 1.020%

    No Known Activations