© 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. 129323
    Prev
    Next
    INDEX
    Explanations

    and

    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
    odem
    -0.25
     dissect
    -0.25
    ordes
    -0.25
    æģŃåĸľ
    -0.24
     subdued
    -0.24
     sodom
    -0.23
     enctype
    -0.23
    udies
    -0.23
     validations
    -0.23
     Äijá»ĩ
    -0.23
    POSITIVE LOGITS
    ä»įåľ¨
    0.28
    åħ·ä½ĵ
    0.27
    cul
    0.26
     Prec
    0.26
    说è¯Ŀ
    0.25
    OF
    0.24
    specified
    0.24
    身边çļĦ
    0.24
    äl
    0.24
     v
    0.23
    Activations Density 12.970%

    No Known Activations