© 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. 21939
    Prev
    Next
    INDEX
    Explanations

    historical contexts

    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
    rapper
    -0.08
     daqui
    -0.08
    çļĦä»Ĭ天
    -0.08
    æıIJéĨĴæĤ¨
    -0.08
    ä¸įè§ī
    -0.08
    è¿ijå¹´
    -0.08
    Snap
    -0.08
     ÙĪÙĨصÙģ
    -0.08
    ä»ĸçİ°åľ¨
    -0.08
    _ACTIONS
    -0.08
    POSITIVE LOGITS
    å½ĵæŶçļĦ
    0.16
    å½ĵæŶ
    0.15
    åľ¨å½ĵæŶ
    0.14
    éĤ£æŶçļĦ
    0.14
    çķ¶æĻĤ
    0.13
    éĤ£æŶåĢĻ
    0.13
    éĤ£æŶ
    0.12
     damals
    0.12
     damal
    0.12
    éĤ£ä¸ªæŶåĢĻ
    0.11
    Activations Density 0.823%

    No Known Activations