© 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. 48345
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and formulas

    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
    omic
    -0.07
    æĪij们éĥ½æĺ¯
    -0.07
    è¦ģçŁ¥éģĵ
    -0.07
    çļĦåħ¶ä»ĸ
    -0.06
    ÙĪز
    -0.06
    ç¿Ķ
    -0.06
    å¾ĢéĩĮ
    -0.06
    om
    -0.06
    æŁIJä¸Ģ个
    -0.06
    åħ¶ä»ĸçļĦ
    -0.06
    POSITIVE LOGITS
    éĿĸ
    0.08
    iffs
    0.08
     vigilant
    0.08
    ä¹ĭåħī
    0.08
    ighted
    0.07
    uckland
    0.07
    egral
    0.07
    éĢļè¿ĩ以ä¸Ĭ
    0.07
    Millis
    0.07
    æĤ¸
    0.07
    Activations Density 0.005%

    No Known Activations