© 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. 12838
    Prev
    Next
    INDEX
    Explanations

    Japanese punctuation and grammatical particles

    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
    çĸ¤
    -0.07
    ihin
    -0.07
    ikal
    -0.07
     conf
    -0.06
    Äįko
    -0.06
    触
    -0.06
     Way
    -0.06
    èĤ¥
    -0.06
     abuse
    -0.06
    åİŁåĪĻä¸Ĭ
    -0.06
    POSITIVE LOGITS
    åıĪæĪĸèĢħ
    0.09
    æĪĸèĢħ
    0.08
    æĪĸèĢħæĺ¯
    0.08
    æĪĸæĺ¯
    0.08
    æĬijæĪĸ
    0.08
    æĪĸèĢħåħ¶ä»ĸ
    0.07
    æĮºå¥½çļĦ
    0.07
    æĮºå¥½
    0.07
    leading
    0.07
    æĪĸåħ¶
    0.07
    Activations Density 0.003%

    No Known Activations