© 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. 20-TRANSCODER-HP
    7. 108480
    Prev
    Next
    INDEX
    Explanations

    Legal, code, news, academic text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦ第ä¸Ģ个
    -0.28
    -prefix
    -0.28
    tring
    -0.28
    ijľ
    -0.26
    /pg
    -0.26
    第ä¸ī个
    -0.24
    ogr
    -0.24
    @brief
    -0.24
     gre
    -0.24
    :red
    -0.24
    POSITIVE LOGITS
    ÇIJ
    0.32
    èħ°
    0.26
    ÇĴ
    0.25
    åIJĦæĸ¹éĿ¢
    0.24
    StringUtil
    0.24
    ients
    0.24
    éĺĴ
    0.24
    á¹ĩ
    0.23
    çļĦä¸ĢåĪĩ
    0.23
    é«ĺ
    0.23
    Activations Density 1.947%

    No Known Activations