© 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. 42763
    Prev
    Next
    INDEX
    Explanations

    comparing things

    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
     ÙĥÙıÙĦ
    -0.07
    æŁIJæŁIJ
    -0.07
    ç´«
    -0.07
    ä½Ĩåı¯ä»¥
    -0.07
    ä»Ģä¹ĪçļĦ
    -0.07
    /cs
    -0.07
    æŁIJä¸Ģ个
    -0.07
    à´´
    -0.07
     Zav
    -0.07
    æ°¸è¿ľçļĦ
    -0.07
    POSITIVE LOGITS
    èĢĮè¿Ļ
    0.07
    rror
    0.07
    ãģªãģ®ãģ§ãģĻ
    0.07
    rokes
    0.07
    èĩªçĦ¶å°±
    0.06
    è½®åĪ°
    0.06
    ript
    0.06
    顺é£İ
    0.06
    icks
    0.06
    ìĭĿìĿ´
    0.06
    Activations Density 0.001%

    No Known Activations