© 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. 30235
    Prev
    Next
    INDEX
    Explanations

    saying or referring

    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
    gov
    -0.07
    äºĨäºĭ
    -0.06
     Harvey
    -0.06
    çŀħ
    -0.06
    æ»´æ»´
    -0.06
    æĺ¯å¦ĤæѤ
    -0.06
     af
    -0.06
    oves
    -0.06
    èĢĮéĤ£äºĽ
    -0.06
     obl
    -0.06
    POSITIVE LOGITS
    æŁIJ人
    0.12
    æŁIJæŁIJ
    0.10
    ulte
    0.09
     casually
    0.09
    æŁIJ个
    0.08
    è¯ĿæĿ¥
    0.08
    æŁIJ
    0.08
    phan
    0.08
    笼
    0.08
    åľ¨æŁIJ
    0.08
    Activations Density 0.044%

    No Known Activations