© 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. 51670
    Prev
    Next
    INDEX
    Explanations

    time taken until

    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
    æŶä¸įæŶ
    -0.10
    azza
    -0.09
     préalable
    -0.08
    ooth
    -0.08
    åĦªåħĪ
    -0.07
    utu
    -0.07
     zeit
    -0.07
    angled
    -0.07
    æĺ¯ä¸Ģç§įéĿŀ常
    -0.07
    INA
    -0.07
    POSITIVE LOGITS
    è¾¾åĪ°
    0.08
     fastest
    0.08
    ä»İä¸Ģ个
    0.07
    积累
    0.07
    å®ĮæĪIJ
    0.07
    èµ°å®Į
    0.07
    积èĵĦ
    0.07
    积累ç»ıéªĮ
    0.07
     complete
    0.07
     reaching
    0.07
    Activations Density 0.042%

    No Known Activations