© 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. 12-TRANSCODER-HP
    7. 22629
    Prev
    Next
    INDEX
    Explanations

    Code/special characters/names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laps
    -0.28
    ç¼¢
    -0.28
    ("^
    -0.26
    itures
    -0.26
    vent
    -0.25
    æijĶ
    -0.25
    æ®Ĭ
    -0.25
    临æŶ
    -0.24
    fld
    -0.24
    èĹ©
    -0.24
    POSITIVE LOGITS
    æĬ¢
    0.30
    .dylib
    0.28
    éĥ¨åī¯
    0.26
     imbalance
    0.25
    ä¸į平衡
    0.25
    ÑģÑĤолÑĮ
    0.25
    æİĴæ°´
    0.25
    æ°´åĪ©å·¥ç¨ĭ
    0.24
    YO
    0.24
    ä»Ĺ
    0.23
    Activations Density 0.001%

    No Known Activations