© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61907
    Prev
    Next
    INDEX
    Explanations

    XML 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
     @}
    -0.08
    à¹Ģร
    -0.07
    çłĤç³ĸ
    -0.07
    edis
    -0.07
    Ñĥм
    -0.07
    èIJ¥éĶĢçŃĸåĪĴ
    -0.07
    å½ĵå½Ĵ
    -0.07
     JAXBElement
    -0.07
    伤çļĦ
    -0.07
    isser
    -0.07
    POSITIVE LOGITS
    ä¾Ľå¤§å®¶
    0.07
    æŨ
    0.07
    pa
    0.07
     اÙĦØŃر
    0.07
    dir
    0.07
    erty
    0.07
    CHIP
    0.07
    #!/
    0.07
    ç±į
    0.06
    LB
    0.06
    Activations Density 0.329%

    No Known Activations