© 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. 27463
    Prev
    Next
    INDEX
    Explanations

    followed by code

    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
    edio
    -0.08
    æĴ²
    -0.07
    æĸĩåѦéĻ¢
    -0.07
    ilik
    -0.07
    èīºæľ¯åĽ¢
    -0.07
    èĢĮæĺĵ
    -0.07
     Ñĩи
    -0.07
    å½±åĵįçļĦ
    -0.07
    åľ¨ä»ĬåIJİ
    -0.07
    INES
    -0.07
    POSITIVE LOGITS
    çĦ¶åIJİæĺ¯
    0.09
    ä¹ĭåIJİ
    0.09
     наÑģÑĤÑĥпаеÑĤ
    0.08
     followed
    0.08
     preceded
    0.08
    ä¹ĭåIJİçļĦ
    0.08
    è¿Ļ个éĺ¶æ®µ
    0.08
    循çݯ
    0.08
    åIJİè¿Ľè¡Į
    0.08
     preced
    0.07
    Activations Density 0.002%

    No Known Activations