© 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. 23386
    Prev
    Next
    INDEX
    Explanations

    Online discussions and article excerpts

    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
    ilib
    -0.27
    éĺ´å½±
    -0.27
    ä¸įä½ı
    -0.26
    ä½ľèĢħæīĢæľī
    -0.26
    forder
    -0.26
    好å¤Ħ
    -0.26
    nerRadius
    -0.26
    /slick
    -0.26
    æĪ³
    -0.25
    ToBounds
    -0.25
    POSITIVE LOGITS
    è¾ħ
    0.27
    èģĭ
    0.27
    upy
    0.24
     Phy
    0.24
     Size
    0.24
    tester
    0.24
     Supported
    0.24
     Babe
    0.24
    cid
    0.23
     somewhere
    0.23
    Activations Density 0.000%

    No Known Activations