© 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. 142093
    Prev
    Next
    INDEX
    Explanations

    programming questions and answers

    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
     altogether
    -0.28
    Łèĥ½
    -0.28
     drive
    -0.27
    à¬Ĩ
    -0.26
     hoạch
    -0.25
    emic
    -0.25
    omin
    -0.25
    .dtype
    -0.25
    èĩ´
    -0.24
    çĶ¨éĢĶ
    -0.24
    POSITIVE LOGITS
    åĥŃ
    0.28
    è¿Ļ个åIJįåŃĹ
    0.27
     patron
    0.26
    æľīå¤ļ大
    0.26
    ï¼Ħ
    0.25
     Patron
    0.25
     suppl
    0.24
    帮ä»ĸ
    0.24
     Patel
    0.24
     Premiership
    0.24
    Activations Density 11.155%

    No Known Activations