© 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. 19996
    Prev
    Next
    INDEX
    Explanations

    è¿Ļæĺ¯ and familiar words or punctuation

    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
    åĨį说äºĨ
    -0.08
    roid
    -0.08
    åį´ä¹Ł
    -0.08
    ÑģÑĤвен
    -0.07
    enci
    -0.07
    æİĴè¡Įæ¦ľåįķ
    -0.07
    eware
    -0.07
    ñana
    -0.07
    æĹłèĻij
    -0.07
    asc
    -0.07
    POSITIVE LOGITS
    è¿Ļæĺ¯ä¸Ģ个
    0.07
    è¿Ļæĺ¯åľ¨
    0.07
    è¿Ļæĺ¯ä¸Ģç§į
    0.07
    è¿Ļæĺ¯ä¸ª
    0.07
     oldukça
    0.07
    ãģĵãĤĮãģ¯
    0.07
     unfamiliar
    0.06
    è¿Ļæĺ¯æĪij们
    0.06
     à¸Ļีà¹Ī
    0.06
    主è¦ģä»İäºĭ
    0.06
    Activations Density 0.009%

    No Known Activations