© 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. 23-TRANSCODER-HP
    7. 24597
    Prev
    Next
    INDEX
    Explanations

    Ye and Ze

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    迹
    -0.26
    ç´ł
    -0.26
    icus
    -0.25
    rides
    -0.25
    cast
    -0.25
    smith
    -0.25
    NING
    -0.24
     Dep
    -0.24
     Ñĥника
    -0.24
    icina
    -0.23
    POSITIVE LOGITS
    æĹ¥æľ¬äºº
    0.26
    è¿Ļ群
    0.25
    è¿Ļ个æĹ¶ä»£
    0.24
    åŁİå¸Ĥåıijå±ķ
    0.24
    ä¸ŃåĽ½å¸Ĥåľº
    0.24
    .mapping
    0.23
    noch
    0.23
    (strict
    0.23
    ä¸Ģå¦Ĥ
    0.23
    å£ģ
    0.23
    Activations Density 0.037%

    No Known Activations