© 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. 22699
    Prev
    Next
    INDEX
    Explanations

    potentially or consequently

    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
    .lazy
    -0.09
    å°½äºĨ
    -0.08
    isse
    -0.08
    é¦ĸåħĪæĺ¯
    -0.08
     chiefly
    -0.08
    ?,?,
    -0.08
    gnore
    -0.07
    æĿ¥ä¸ºå¤§å®¶
    -0.07
    ftware
    -0.07
    ensity
    -0.07
    POSITIVE LOGITS
     also
    0.08
    建ç«ĭä¸Ģ个
    0.07
    è¿Ļä¹Ł
    0.07
    æĽ´
    0.07
     further
    0.07
    ëĿ¼ëıĦ
    0.07
    æľī趣çļĦæĺ¯
    0.07
    änd
    0.07
    alte
    0.07
    aal
    0.07
    Activations Density 0.006%

    No Known Activations