© 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. 129212
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    uh
    -0.30
    /wiki
    -0.26
    ño
    -0.26
    好è¿IJ
    -0.26
    ubi
    -0.26
    æīĵãģ¡
    -0.26
    èijĹ
    -0.25
    oves
    -0.25
    /archive
    -0.25
    /master
    -0.24
    POSITIVE LOGITS
     Durch
    0.29
    èĩ³ä»Ĭ
    0.29
     casting
    0.27
    ÑģÑĤоÑı
    0.26
     demean
    0.26
    æľīåĬĽ
    0.26
    èĩ³å°ij
    0.26
    ätt
    0.25
     deficit
    0.25
    TypeDef
    0.25
    Activations Density 16.409%

    No Known Activations