© 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. 894
    Prev
    Next
    INDEX
    Explanations

    public class or function declaration

    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
    纲è¦ģ
    -0.08
    tram
    -0.08
    urry
    -0.07
    اÙĨÙĬØ©
    -0.07
    once
    -0.07
    werp
    -0.07
    )arg
    -0.07
    ihad
    -0.07
    <<<<<<<<
    -0.07
     once
    -0.07
    POSITIVE LOGITS
    彩
    0.07
    ç»Ħç»ĩåĴĮ
    0.07
    utter
    0.06
     lookup
    0.06
    ä¸Ģçľ¼
    0.06
    æĻĵ举
    0.06
    é¢Ħå¤ĩ
    0.06
    该æľīçļĦ
    0.06
    Ïĥι
    0.06
    institu
    0.06
    Activations Density 0.007%

    No Known Activations