© 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. 32-TRANSCODER-HP
    7. 43592
    Prev
    Next
    INDEX
    Explanations

    nanotechnology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aired
    -0.29
     lip
    -0.27
     spo
    -0.26
     join
    -0.26
    æĮģå¹³
    -0.26
    ìĭľìĬ¤
    -0.26
     concede
    -0.26
    è¿Ľé¡¹
    -0.25
     equivalents
    -0.25
     alike
    -0.25
    POSITIVE LOGITS
     scientist
    0.29
    eff
    0.29
    çłĤ
    0.29
     scientists
    0.29
    æ¯Ĵç´ł
    0.28
    åľ¨è¿Ļæĸ¹éĿ¢
    0.28
     blades
    0.28
    ç§ij
    0.28
     Blades
    0.28
     Scientists
    0.28
    Activations Density 0.003%

    No Known Activations