© 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. 106967
    Prev
    Next
    INDEX
    Explanations

    Code and symbols

    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
    awns
    -0.28
    èļ¤
    -0.28
    uvre
    -0.26
    让æĤ¨
    -0.26
    çļĦåIJĮåѦ
    -0.25
    ä¸Ģè·¯
    -0.25
    éĤ£ç§į
    -0.25
    å½¼æѤ
    -0.24
    SetText
    -0.24
    imed
    -0.24
    POSITIVE LOGITS
     soap
    0.29
     sin
    0.29
    ain
    0.27
     elasticity
    0.26
    sin
    0.26
    lico
    0.26
    so
    0.26
    soap
    0.25
    (mean
    0.24
    .to
    0.23
    Activations Density 67.993%

    No Known Activations