© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22301
    Prev
    Next
    INDEX
    Explanations

    Kin

    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
    æģŃæķ¬
    -0.27
    ource
    -0.27
    Gram
    -0.26
    wap
    -0.25
    åŃĿ
    -0.25
     Source
    -0.25
     brushed
    -0.24
    Hamilton
    -0.24
    ä¸įå½ĵ
    -0.24
    è·¨
    -0.24
    POSITIVE LOGITS
    ç§ijæĬĢåĽŃ
    0.33
    è¿IJç®Ĺ
    0.26
    測
    0.25
    Ĥ¤
    0.25
    -ass
    0.24
    ogl
    0.24
    ennie
    0.24
    åĩ¹
    0.24
     ASS
    0.24
    decltype
    0.24
    Activations Density 0.009%

    No Known Activations