© 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. 142489
    Prev
    Next
    INDEX
    Explanations

    computer programming

    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
    =_("
    -0.25
     ours
    -0.25
     Fans
    -0.25
     ấy
    -0.25
    erox
    -0.25
     fans
    -0.25
    elson
    -0.24
    ноÑģÑĤей
    -0.24
    loader
    -0.24
    ']->
    -0.24
    POSITIVE LOGITS
    unt
    0.30
    UNT
    0.29
     dyn
    0.26
    è°ĭ
    0.26
    erah
    0.25
     tet
    0.25
     sup
    0.25
    æĶ¶èİ·
    0.25
    çŀ¬éĹ´
    0.25
    ients
    0.25
    Activations Density 5.989%

    No Known Activations