© 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. 40120
    Prev
    Next
    INDEX
    Explanations

    encountering people or things

    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
    åĿIJéķĩ
    -0.08
    室åĨħ空æ°Ķ
    -0.08
    æĬĺèħ¾
    -0.08
    åľ¨åºĬä¸Ĭ
    -0.07
     internal
    -0.07
    æĪ¿éĹ´éĩĮ
    -0.07
    åľ¨éĩĮéĿ¢
    -0.07
    å±ĭåŃIJéĩĮ
    -0.07
    éĶħåĨħ
    -0.07
    åĨħéĥ¨
    -0.07
    POSITIVE LOGITS
    åģ¶éģĩ
    0.11
    æĭ¦
    0.11
    å¥ĩéģĩ
    0.10
    驻足
    0.10
     ÑģлÑĥÑĩайно
    0.10
     encountered
    0.10
     пÑĢоÑħо
    0.10
    æĭ¦ä½ı
    0.09
    路边
    0.09
    éģĩåĪ°çļĦ
    0.09
    Activations Density 0.472%

    No Known Activations