© 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. 42202
    Prev
    Next
    INDEX
    Explanations

    programming context, symbols, 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
    ä¸Ģé¢Ĺ
    -0.07
    ymm
    -0.07
     Betr
    -0.07
    æľīä¸Ģé¢Ĺ
    -0.07
    ä¸Ģé¡Ĩ
    -0.07
    ä¸ĢèĤ¡
    -0.06
    _testing
    -0.06
    _specs
    -0.06
     اÙĦتش
    -0.06
    igan
    -0.06
    POSITIVE LOGITS
    xim
    0.08
    æ¯ı个人
    0.08
    æ¯ı家
    0.08
    æģº
    0.08
    æ¯ıä¸Ģ个人
    0.08
    纾
    0.08
    each
    0.08
     denun
    0.08
    ä»
    0.07
    inger
    0.07
    Activations Density 0.111%

    No Known Activations