© 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. 129897
    Prev
    Next
    INDEX
    Explanations

    Numbers in patents

    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
    .Lib
    -0.29
    orca
    -0.28
    ималÑĮ
    -0.27
    ]=>
    -0.27
    because
    -0.25
    Ã¤ÃŁ
    -0.25
    åĽłä¸ºåľ¨
    -0.24
    ĪæĿĥ
    -0.24
    eton
    -0.24
    éĴĬ
    -0.24
    POSITIVE LOGITS
    æĹ¥å¤ľ
    0.25
    vine
    0.24
    &e
    0.24
    &
    0.23
    --,
    0.23
     repro
    0.23
     Gar
    0.23
    æľĢåIJİ
    0.23
    åħĭ
    0.22
    Ļ¶
    0.22
    Activations Density 74.608%

    No Known Activations