© 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. 108486
    Prev
    Next
    INDEX
    Explanations

    Technical language

    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
    ä¸ĢåĪĩ
    -0.27
     exactly
    -0.26
    masını
    -0.25
     skips
    -0.25
    _sector
    -0.24
    auty
    -0.24
    anguard
    -0.24
     proves
    -0.24
    trail
    -0.24
    _since
    -0.24
    POSITIVE LOGITS
    大èĩ´
    0.44
    估计
    0.43
     largely
    0.43
     roughly
    0.42
    大æ¦Ĥ
    0.40
    å·®ä¸įå¤ļ
    0.40
     approximate
    0.38
    å°½éĩı
    0.35
     nearly
    0.34
     approximately
    0.34
    Activations Density 76.701%

    No Known Activations