© 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. 43372
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ï¼ĮåĪĻ
    -0.31
    éĥ½ä¸į
    -0.29
    è¿Ļæł·çļĦ
    -0.28
    è¿Ļæł·ä¸Ģ个
    -0.28
    éĥ½ä¸įä¼ļ
    -0.28
    è¿Ļæł·
    -0.28
    åħ·æľī
    -0.27
    ï¼Įåľ¨
    -0.27
    éĥ½æľī
    -0.26
    è¿Ļæł·çļĦè¯Ŀ
    -0.26
    POSITIVE LOGITS
    tha
    0.34
    _that
    0.32
     that
    0.30
    That
    0.29
     growth
    0.28
    _THAT
    0.28
    <this
    0.28
    “That
    0.27
    that
    0.27
    evin
    0.27
    Activations Density 0.006%

    No Known Activations