© 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. 16701
    Prev
    Next
    INDEX
    Explanations

    symbols and 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
    ired
    -0.09
    amma
    -0.08
    好åѦçĶŁ
    -0.08
    è¦ļ
    -0.08
    igny
    -0.07
    urado
    -0.07
    åįĩåĪĿ
    -0.07
     Cant
    -0.07
    phan
    -0.07
    ÏĢη
    -0.07
    POSITIVE LOGITS
    ä½ķåĨµ
    0.09
    rof
    0.06
    ç»ıåİĨ
    0.06
    estroy
    0.06
     наконеÑĨ
    0.06
    itere
    0.06
     enfin
    0.06
    ç»Īäºİ
    0.06
    æĽ´ä½ķåĨµ
    0.06
     ÑģÑĤаж
    0.06
    Activations Density 0.004%

    No Known Activations