© 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. 129104
    Prev
    Next
    INDEX
    Explanations

    Aub

    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
     nothing
    -0.32
    nothing
    -0.28
    inge
    -0.28
     more
    -0.28
     Quad
    -0.27
     anything
    -0.27
     long
    -0.27
     respect
    -0.27
    ä¸įåŃĺåľ¨
    -0.26
    aven
    -0.25
    POSITIVE LOGITS
    å§ĵ
    0.26
    Ậ
    0.26
    æ··æ·Ĩ
    0.25
    æĹģ
    0.25
    eros
    0.24
    ypo
    0.24
    bnb
    0.24
    褶
    0.24
    Ãły
    0.23
    yps
    0.23
    Activations Density 0.756%

    No Known Activations