© 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. 41619
    Prev
    Next
    INDEX
    Explanations

    punctuation and 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
    çļĦåı¯èĥ½
    -0.08
    GRID
    -0.08
    ë¡
    -0.08
     Millenn
    -0.08
    ำ
    -0.07
    ä¹ĭçľ¼
    -0.07
    oker
    -0.07
    atr
    -0.07
    类似éĹ®é¢ĺ
    -0.07
    Domains
    -0.07
    POSITIVE LOGITS
    Âł
    0.08
    ahoma
    0.06
    acob
    0.06
    è£ĺ
    0.06
    agar
    0.06
    GW
    0.06
    Ø·ÙĤ
    0.06
    æļ§
    0.06
    羣çļĦ好
    0.06
     envol
    0.06
    Activations Density 0.415%

    No Known Activations