© 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. 142518
    Prev
    Next
    INDEX
    Explanations

    But

    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
    Negative Logits
    è¶Ł
    -0.30
     Ala
    -0.26
     dilig
    -0.26
    åıijçİ°éĹ®é¢ĺ
    -0.26
    /Library
    -0.25
    è£ħçĶ²
    -0.24
    (Some
    -0.23
    æĽ´å¤ļ精彩
    -0.23
     emanc
    -0.23
     Bank
    -0.23
    POSITIVE LOGITS
     isolation
    0.27
    abinet
    0.27
    lee
    0.26
    ief
    0.25
     conveniently
    0.24
    immer
    0.24
    uset
    0.24
    ongan
    0.24
    çªģå¦Ĥåħ¶æĿ¥
    0.23
    èĢľ
    0.23
    Activations Density 23.657%

    No Known Activations