© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42478
    Prev
    Next
    INDEX
    Explanations

    explicit optimization

    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
    named
    -0.08
    pron
    -0.08
    è¿ĻäºĽä¸ľè¥¿
    -0.07
    âĸłâĸł
    -0.07
    人åijĺåIJįåįķ
    -0.07
    ngine
    -0.07
    dia
    -0.07
     resides
    -0.06
    IFO
    -0.06
    ria
    -0.06
    POSITIVE LOGITS
    è¦ģæ±Ĥ
    0.10
     requirement
    0.10
    è¦ģæ±Ĥåľ¨
    0.10
    çļĦè¦ģæ±Ĥ
    0.09
    Require
    0.09
     require
    0.09
     demanding
    0.09
     demands
    0.09
     equality
    0.09
    ä¸¥æł¼è¦ģæ±Ĥ
    0.09
    Activations Density 0.003%

    No Known Activations