© 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. 22152
    Prev
    Next
    INDEX
    Explanations

    Railroads

    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
    Negative Logits
    èĦ«
    -0.27
     Saved
    -0.27
     tuyến
    -0.25
    izzo
    -0.25
     Gingrich
    -0.25
    åĵªç§į
    -0.24
    ropol
    -0.24
     lanes
    -0.24
    fäh
    -0.24
     Lands
    -0.23
    POSITIVE LOGITS
    æ¼ı
    0.33
    éŃħ
    0.30
    ä¸įä¸ĭ
    0.29
    å¤ĸ壳
    0.27
    crow
    0.27
    æł¸
    0.26
    Pour
    0.26
    æĢĢæĬ±
    0.25
    spr
    0.25
     crowd
    0.24
    Activations Density 0.004%

    No Known Activations