© 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. 20-TRANSCODER-HP
    7. 63132
    Prev
    Next
    INDEX
    Explanations

    Higher education and hospitals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Savage
    -0.27
    ä¸įè¿ľ
    -0.27
    éĻįèIJ½
    -0.26
    boot
    -0.26
     Stück
    -0.25
    ////////////////////////////////////////////////////////////////////
    -0.25
    åIJ¯
    -0.24
     Street
    -0.24
    ä¸ĢæŃ¥æŃ¥
    -0.24
     boot
    -0.23
    POSITIVE LOGITS
    ез
    0.26
     lob
    0.25
    ible
    0.25
    lish
    0.25
    etrize
    0.24
    ÙĦØ©
    0.24
    amerate
    0.24
    ponsive
    0.23
    -transitional
    0.23
    fulWidget
    0.23
    Activations Density 11.917%

    No Known Activations