© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107790
    Prev
    Next
    INDEX
    Explanations

    Transcripts/legal proceedings

    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
    Not in Any Lists

    No Comments

    Negative Logits
    olics
    -0.29
    ä¸Ĭè°ĥ
    -0.28
    udem
    -0.27
    ç«Ń
    -0.27
    æķĻç¨ĭ
    -0.26
    ä¸Ģç¯ĩæĸĩç«ł
    -0.26
    éļ§
    -0.26
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.26
    äºĭåIJİ
    -0.25
    ä¸Ģ件äºĭæĥħ
    -0.25
    POSITIVE LOGITS
    aland
    0.30
     capped
    0.30
    eurs
    0.27
    _caps
    0.27
    caps
    0.26
    ena
    0.26
    енÑĤа
    0.25
    èĬĿåĬł
    0.24
    PELL
    0.24
    带æĿ¥äºĨ
    0.24
    Activations Density 0.616%

    No Known Activations