© 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. 142715
    Prev
    Next
    INDEX
    Explanations

    programming 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
     Edmund
    -0.29
    ician
    -0.26
     almond
    -0.26
    Mutable
    -0.26
     thaw
    -0.25
    碣
    -0.25
    ç»´å¥ĩ
    -0.25
     collaborate
    -0.24
    人çī©
    -0.24
     collaborations
    -0.24
    POSITIVE LOGITS
    )++;↵
    0.26
    inha
    0.26
    表éĿ¢ä¸Ĭ
    0.26
    ]--;↵
    0.25
     mop
    0.24
    æĸ½è¡Į
    0.23
    æĸĮ
    0.23
    ipay
    0.23
     postponed
    0.22
    -Ch
    0.22
    Activations Density 5.331%

    No Known Activations