© 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. 22526
    Prev
    Next
    INDEX
    Explanations

    grammatical categories

    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
    è£ı
    -0.08
    uris
    -0.07
    èĨĽ
    -0.07
     outs
    -0.07
    aros
    -0.07
    æĿ¥ä¿¡
    -0.07
    tti
    -0.06
    èĦ±ä¸ĭ
    -0.06
    mania
    -0.06
    -threatening
    -0.06
    POSITIVE LOGITS
    ìį¨
    0.09
    ailer
    0.08
    çļĦ使çĶ¨
    0.08
    è¨Ģæĥħ
    0.08
    ampir
    0.07
    常éĩı
    0.07
    tect
    0.07
    à¸ģำà¸ģัà¸ļ
    0.07
     ë¶Ļ
    0.07
    çļĦ身影
    0.07
    Activations Density 0.016%

    No Known Activations