© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7069
    Prev
    Next
    INDEX
    Explanations

    proper nouns and technical terms

    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
    Negative Logits
    为ä¿Ŀè¯ģ
    -0.07
     respective
    -0.06
     either
    -0.06
    ог
    -0.06
    ags
    -0.06
    æ¾³
    -0.06
    agina
    -0.06
    ometrics
    -0.06
    дал
    -0.06
    etz
    -0.06
    POSITIVE LOGITS
     essenz
    0.08
    å¼ķ人åħ¥
    0.07
    éĺħè¯»æľ¬æĸĩ
    0.07
    piegel
    0.07
    ä¹ĭ忧
    0.07
    æľ¬è´¨ä¸Ĭ
    0.07
    amat
    0.07
    æĿ¥ä¸ºå¤§å®¶
    0.07
    æĬ¥è®¯
    0.07
    è¦ģä»İ
    0.07
    Activations Density 0.059%

    No Known Activations