© 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. 34352
    Prev
    Next
    INDEX
    Explanations

    [@B1] citations

    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
    ley
    -0.07
    è´±
    -0.07
    殿
    -0.07
    æĮ¯
    -0.07
    olt
    -0.07
    éĴ°
    -0.07
    gon
    -0.06
    en
    -0.06
    家家
    -0.06
    æĮĩ示
    -0.06
    POSITIVE LOGITS
    伤èĢħ
    0.08
    ç·©
    0.07
    æĶĿ
    0.07
     #__
    0.07
    END
    0.07
    çģ«äºĨ
    0.07
    ä¸įä½ıäºĨ
    0.07
    gable
    0.07
    è®¤çľŁç»Ħç»ĩ
    0.07
    ç¼®
    0.07
    Activations Density 0.129%

    No Known Activations