© 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. 12-TRANSCODER-HP
    7. 23305
    Prev
    Next
    INDEX
    Explanations

    heme

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADVERTISEMENT
    -0.30
    nds
    -0.29
     gener
    -0.27
    //{{
    -0.26
    pdev
    -0.26
     initState
    -0.26
    ä¸Ĭä¸ĭ
    -0.24
    ailer
    -0.23
    å·¦åı³
    -0.23
     decentralized
    -0.23
    POSITIVE LOGITS
    ä¸ĢæĿ¡
    0.28
    第ä¸ĢæĿ¡
    0.28
    ä¸Ģæ¢Ŀ
    0.27
    æ¯Ķäºļ
    0.25
    hell
    0.25
    POOL
    0.24
    æ½Ń
    0.24
    .lex
    0.24
    lers
    0.24
    unnel
    0.24
    Activations Density 0.006%

    No Known Activations