© 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. 130473
    Prev
    Next
    INDEX
    Explanations

    Formal documents

    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
    æĹ¢èĥ½
    -0.29
    ä¸ĩ象
    -0.28
    phony
    -0.27
    Mob
    -0.26
    æľīèĥ½åĬĽ
    -0.25
    æĹ¢åı¯ä»¥
    -0.25
    resident
    -0.24
    æĹ¢
    -0.24
    unky
    -0.23
    åĨĻåŃĹ
    -0.23
    POSITIVE LOGITS
    aday
    0.27
    è¿Ľåĩº
    0.26
    æĶ¶
    0.24
    æĮĩçļĦæĺ¯
    0.24
    缴è§Ĥ
    0.24
    åİī
    0.23
    çļĦå°ı
    0.23
    çļĦæ¨¡æł·
    0.23
    ?url
    0.23
    ;background
    0.23
    Activations Density 7.546%

    No Known Activations