© 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. 64690
    Prev
    Next
    INDEX
    Explanations

    technical questions and answers

    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
    çł´
    -0.28
     Level
    -0.27
    æ´İ
    -0.26
    иденÑĤ
    -0.25
    .Level
    -0.25
    èĩªæĦ¿
    -0.25
    æµĶ
    -0.25
    åIJĮåŁİ
    -0.24
    fon
    -0.24
    .dest
    -0.24
    POSITIVE LOGITS
    æ¯Ķä¾ĭ
    0.47
    çļĦæ¯Ķä¾ĭ
    0.44
    åįłæ¯Ķ
    0.42
     proportion
    0.37
     proportions
    0.36
    为主çļĦ
    0.36
     dominant
    0.36
     ratio
    0.34
     dominated
    0.34
     dominance
    0.33
    Activations Density 33.885%

    No Known Activations