© 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. 43650
    Prev
    Next
    INDEX
    Explanations

    scientific measurements

    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
    éĥ½ä¼ļ
    -0.30
    éĥ½ä¼ļæľī
    -0.29
    éĥ½è§īå¾Ĺ
    -0.25
     eventual
    -0.25
    è¿Ļç§įæĸ¹å¼ı
    -0.25
    ä¿«
    -0.24
     rallying
    -0.24
    éĥ½åı¯ä»¥
    -0.23
    æĿ°åĩº
    -0.23
     Gew
    -0.23
    POSITIVE LOGITS
     both
    0.41
     accurately
    0.40
     efficiently
    0.39
     below
    0.36
     thoroughly
    0.35
    both
    0.34
     above
    0.33
     rapidly
    0.33
     BOTH
    0.32
     faster
    0.32
    Activations Density 0.001%

    No Known Activations