© 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. 108529
    Prev
    Next
    INDEX
    Explanations

    Excerpts from larger documents

    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
    æĹłç©·
    -0.30
    æĦļ
    -0.28
     simult
    -0.26
    åįļå¼Ī
    -0.26
    idan
    -0.26
    ÙĦس
    -0.25
    åŃ¦æľŁ
    -0.25
    æĺŃ
    -0.24
     infinite
    -0.24
     Sasha
    -0.24
    POSITIVE LOGITS
    åı·åı¬
    0.27
    åį´è¢«
    0.26
    callbacks
    0.26
    gence
    0.26
    å¾Īåĸľæ¬¢
    0.26
    _marks
    0.26
    oden
    0.25
    ä¹Łæľīä¸ĢäºĽ
    0.25
     recommendations
    0.25
     encouraged
    0.25
    Activations Density 4.690%

    No Known Activations