© 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. 64849
    Prev
    Next
    INDEX
    Explanations

    code

    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
     liv
    -0.29
     gui
    -0.28
    plevel
    -0.24
    æĻļé¤IJ
    -0.24
     pavement
    -0.24
    ypical
    -0.24
     dag
    -0.24
    åħ¶éĹ´
    -0.24
    身å¿ĥåģ¥åº·
    -0.23
     stom
    -0.23
    POSITIVE LOGITS
    ohana
    0.28
     tally
    0.27
    äºĨåIJĹ
    0.27
    .Compose
    0.27
    etto
    0.26
    æĿĥ
    0.26
    è¡¥åģ¿
    0.25
    .Roles
    0.25
     TORT
    0.25
    itto
    0.24
    Activations Density 1.254%

    No Known Activations