© 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. 16256
    Prev
    Next
    INDEX
    Explanations

    code generation and structure

    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
    OrFail
    -0.08
    éĢļä¿Ĺ
    -0.07
    æĽ¿ä»ĸ
    -0.07
    ×ķ×Ĺ
    -0.07
    åĪ©çī©
    -0.07
    ç»Ŀåľ°
    -0.07
    idah
    -0.07
    ±ħ
    -0.07
    uyá»ĩt
    -0.07
    ĺ
    -0.07
    POSITIVE LOGITS
    bero
    0.07
     undone
    0.06
     shake
    0.06
    _COUNTER
    0.06
     Humb
    0.06
    optional
    0.06
     évent
    0.06
     unset
    0.06
    пов
    0.06
    åľ¨åIJĦ个
    0.06
    Activations Density 0.407%

    No Known Activations