© 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. 129045
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    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
    æ¥ŀ
    -0.28
    -Feb
    -0.28
    æĭ¼éŁ³
    -0.26
    гоÑĢ
    -0.25
    åķª
    -0.25
    æĸ¹åľĨ
    -0.25
     Canton
    -0.24
    anse
    -0.24
    Caught
    -0.24
    æŁIJ
    -0.23
    POSITIVE LOGITS
    ascript
    0.32
    è¿Ļ个æĹ¶ä»£
    0.29
    igr
    0.27
     foot
    0.26
    utr
    0.24
    oper
    0.23
     EventArgs
    0.23
    emean
    0.23
    ownt
    0.23
    æłĩ
    0.23
    Activations Density 38.069%

    No Known Activations