© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63358
    Prev
    Next
    INDEX
    Explanations

    code comment followed by operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīĢ以çİ°åľ¨
    -0.07
    æīĢ以就
    -0.07
    å±±æ¹ĸ
    -0.07
    ä¹ĭæŃĮ
    -0.07
    plet
    -0.07
    оÑĢг
    -0.06
    .ft
    -0.06
    ãģ£ãģįãĤĬ
    -0.06
    æĩĤ
    -0.06
    amal
    -0.06
    POSITIVE LOGITS
    èĴĤæĸ¯
    0.07
    áh
    0.07
    ês
    0.07
    udes
    0.06
    红èī²åŁºåĽł
    0.06
    entifier
    0.06
    æijĨæīĭ
    0.06
    mä
    0.06
    enske
    0.06
    Lö
    0.06
    Activations Density 0.007%

    No Known Activations