© 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. 2599
    Prev
    Next
    INDEX
    Explanations

    style and enhancement

    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
    æľĢæĹ©
    -0.07
    èī¯å¿ĥ
    -0.06
     earliest
    -0.06
    æĪªèĩ³
    -0.06
    -0.06
    éĿ¢çĽ®
    -0.06
    amak
    -0.06
    åŃIJå¼Ł
    -0.06
     conduct
    -0.06
    å¤ĸ表
    -0.06
    POSITIVE LOGITS
    åı¯ä»¥èµ·åĪ°
    0.09
    ì¹
    0.09
    æ°Ķåľº
    0.09
     Absol
    0.09
     ÑģмоÑĤÑĢиÑĤÑģÑı
    0.09
    panse
    0.09
    å°ıæĪ·åŀĭ
    0.09
    баланÑģи
    0.09
    èī²ç³»
    0.09
    空éĸĵ
    0.09
    Activations Density 0.117%

    No Known Activations