© 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. 64550
    Prev
    Next
    INDEX
    Explanations

    Research/Scientific Publications

    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
    å¾®
    -0.27
    arch
    -0.27
    archs
    -0.27
    ----
    -0.27
    æŀĿ
    -0.26
    гин
    -0.26
    usa
    -0.26
    udem
    -0.26
    udi
    -0.25
    ----↵↵
    -0.25
    POSITIVE LOGITS
    è¿ĩåī©
    0.27
    .RunWith
    0.25
     funny
    0.25
     Buckley
    0.25
    promise
    0.25
    _IE
    0.24
    Fcn
    0.24
    .fromLTRB
    0.24
    åIJijãģį
    0.24
    æį¢ä¸ª
    0.24
    Activations Density 2.793%

    No Known Activations