© 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. 129209
    Prev
    Next
    INDEX
    Explanations

    but

    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
    åį´æ²¡æľī
    -0.32
    åIJĮæĥħ
    -0.31
    ç½¢äºĨ
    -0.31
     DOES
    -0.30
    æĨ¾
    -0.28
    åį´ä¸į
    -0.28
    èĢĮå·²
    -0.28
    éĥ½æĹłæ³ķ
    -0.28
    composite
    -0.27
     saja
    -0.26
    POSITIVE LOGITS
     untouched
    0.28
    redient
    0.26
     unin
    0.25
    /MIT
    0.24
     Papers
    0.24
    dfd
    0.24
     BRAND
    0.24
    å§Ĵ
    0.24
    entimes
    0.24
     inv
    0.24
    Activations Density 10.959%

    No Known Activations