© 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. 1130
    Prev
    Next
    INDEX
    Explanations

    result

    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
    缸è¾ħ缸æĪIJ
    -0.06
    åī¥
    -0.06
    èįĨæ£ĺ
    -0.06
    好åŃ©åŃIJ
    -0.06
    onia
    -0.06
     pes
    -0.06
    æĸ¹æ³ķæĿ¥
    -0.06
    ÙĴرÙIJ
    -0.06
    /
    -0.06
    uds
    -0.06
    POSITIVE LOGITS
    /result
    0.10
    åı¯æĥ³èĢĮçŁ¥
    0.09
    eri
    0.09
    TURE
    0.08
    uket
    0.08
    åĴĮ建议
    0.08
    /results
    0.08
    дÑİ
    0.08
    ssize
    0.08
    igno
    0.07
    Activations Density 0.016%

    No Known Activations