© 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. 39581
    Prev
    Next
    INDEX
    Explanations

    August years

    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
    ä¸Ĭä¸Ģ页
    -0.08
    åīį两
    -0.07
    åĪ°çĿĢ
    -0.07
    omos
    -0.07
     Tucker
    -0.07
    óta
    -0.07
    åĪ°èĢģ
    -0.07
    ç»Ħç»ĩçļĦ
    -0.07
    ~=
    -0.06
     POV
    -0.06
    POSITIVE LOGITS
    æľŁéĹ´
    0.12
    æľŁéĸĵ
    0.12
    æľŁéĹ´çļĦ
    0.12
    æĹ¥æľŁéĹ´
    0.11
    è¿Ļ段æŶéĹ´
    0.10
    ä¹ĭéĸĵ
    0.10
    ä¹ĭéĹ´
    0.09
    è¿Ļ段
    0.09
    è¿ĻæľŁéĹ´
    0.09
    ä¹ĭéĹ´åŃĺåľ¨
    0.09
    Activations Density 0.203%

    No Known Activations