© 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. 140710
    Prev
    Next
    INDEX
    Explanations

    giving

    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
    ä¸Ģç¢Ĺ
    -0.28
    ulf
    -0.28
    ì¶ķ
    -0.27
    ä¸ĢéĶ®
    -0.27
    æĬĢæľ¯åĴĮ
    -0.26
    ient
    -0.25
    æݪ
    -0.25
    _coeffs
    -0.25
    ats
    -0.25
    å®ŀè´¨
    -0.25
    POSITIVE LOGITS
    mates
    0.28
    inium
    0.28
    翳
    0.27
    imited
    0.25
     Compatibility
    0.25
    ytt
    0.25
    磬
    0.25
    flate
    0.25
    Boom
    0.24
     comments
    0.23
    Activations Density 13.843%

    No Known Activations