© 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. 107845
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    gradation
    -0.24
    éĽ³
    -0.23
    gram
    -0.23
     rage
    -0.23
    mons
    -0.23
    éļıæīĭ
    -0.23
    åģ¥åħ¨
    -0.22
    [Index
    -0.22
    ç§įåŃIJ
    -0.22
    ç¾¤å²Ľ
    -0.22
    POSITIVE LOGITS
     urgently
    0.26
    ç»ıæµİåŃ¦å®¶
    0.25
    udies
    0.25
    对ä¸įèµ·
    0.24
    éĺ¿å§¨
    0.24
    squ
    0.23
     restarted
    0.23
    Ahead
    0.23
    ä¸įæĥľ
    0.23
    Ped
    0.23
    Activations Density 0.021%

    No Known Activations