© 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. 4779
    Prev
    Next
    INDEX
    Explanations

    transcription, time, derivative

    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
     horny
    -0.07
    ä¹ĭæ³ķ
    -0.06
    oline
    -0.06
     تÙĦÙģ
    -0.06
    ä½ľçŃĶ
    -0.06
    大ä¸ĸçķĮ
    -0.06
     Rever
    -0.06
    大æ³ķ
    -0.06
    主è¦ģ
    -0.06
    æĸ¹æ³ķåıĬ
    -0.06
    POSITIVE LOGITS
    #ad
    0.08
    inct
    0.08
    èĤª
    0.08
    ultip
    0.08
    xBC
    0.08
    rientation
    0.08
    າàºĻ
    0.07
    rul
    0.07
    _LVL
    0.07
    anye
    0.07
    Activations Density 0.001%

    No Known Activations