© 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. 25-TRANSCODER-HP
    7. 108641
    Prev
    Next
    INDEX
    Explanations

    code/document fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīĵçĿĢ
    -0.33
    asters
    -0.30
    ç©¿
    -0.30
    PERT
    -0.28
    æķĻè®Ń
    -0.28
    æĬ¥è®°èĢħ
    -0.27
     Debate
    -0.27
    istical
    -0.27
    bris
    -0.27
    acas
    -0.26
    POSITIVE LOGITS
    comb
    0.27
    è¿ĩæĪ·
    0.27
    enburg
    0.25
     discontin
    0.25
    å¾Ħ
    0.25
    usp
    0.24
    ee
    0.24
    enberg
    0.24
    æĹłéĻIJ
    0.24
    iva
    0.24
    Activations Density 0.917%

    No Known Activations