© 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. 33751
    Prev
    Next
    INDEX
    Explanations

    non-english characters

    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
     ugyanis
    -0.07
    æľ¬æĸĩéĵ¾æİ¥
    -0.07
    ç½Ħ
    -0.06
     captive
    -0.06
    urch
    -0.06
    __((
    -0.06
    çļĦä¸Ģæĸ¹
    -0.06
    åľ¨ä¸Ģå®ļç¨ĭ度ä¸Ĭ
    -0.06
    åľ¨åIJİ
    -0.06
    еÑģÑĤв
    -0.06
    POSITIVE LOGITS
    agh
    0.09
    ãģµ
    0.08
    agos
    0.08
    ago
    0.08
     Gob
    0.07
    åįķå±Ĥ
    0.07
    utas
    0.07
    积æŀģä¸İ
    0.07
    pte
    0.07
    åİļçĪ±
    0.07
    Activations Density 0.002%

    No Known Activations