© 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. 106825
    Prev
    Next
    INDEX
    Explanations

    Code and disorganized 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
    Negative Logits
    æĪIJé¾Ļ
    -0.28
    æľīä¸Ģä½į
    -0.26
    æĮĩçĤ¹
    -0.25
    è¦ģçĤ¹
    -0.24
     doubts
    -0.24
     dub
    -0.24
    GRP
    -0.23
     вÑĢа
    -0.23
    好æĦŁ
    -0.23
    director
    -0.23
    POSITIVE LOGITS
    çļĦæĺ¯
    0.28
     Chronicles
    0.27
    ÂŃs
    0.26
    ç«ł
    0.25
    uffle
    0.25
    pez
    0.24
    (assert
    0.24
    (JS
    0.24
    /&
    0.24
    .opend
    0.23
    Activations Density 25.840%

    No Known Activations