© 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. 30-TRANSCODER-HP
    7. 95982
    Prev
    Next
    INDEX
    Explanations

    fishing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¸ıå®ŀ
    -0.27
    ç¨İåĬ¡æĢ»å±Ģ
    -0.27
    å¡Į
    -0.26
    wave
    -0.26
    addresses
    -0.25
    çŀª
    -0.25
    èĥĮæĻ¯
    -0.24
    Prem
    -0.24
    urls
    -0.24
    àªĹ
    -0.24
    POSITIVE LOGITS
    olls
    0.29
    æ®ĭ
    0.28
    inary
    0.28
     marc
    0.28
    виÑĤ
    0.27
    ä¿®
    0.26
    ilik
    0.26
     Treat
    0.26
    heimer
    0.25
    afx
    0.25
    Activations Density 0.104%

    No Known Activations