© 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. 31799
    Prev
    Next
    INDEX
    Explanations

    time and space complexity

    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
    ÑģкÑĢÑĭ
    -0.08
    æ±Łå±±
    -0.08
    红æĹĹ
    -0.07
    éķ¿éķ¿
    -0.07
    åĦ¿çļĦ
    -0.07
    èģĶæĴŃ
    -0.07
    ELS
    -0.07
    å¦ĤçĥŁ
    -0.07
     ÙĪاÙĦÙħر
    -0.07
    requ
    -0.07
    POSITIVE LOGITS
    °
    0.07
    àºĶ
    0.07
    kan
    0.07
    åŃ¸å®¶
    0.07
    è¢ĭ
    0.07
    hift
    0.07
    çļĦãģ«ãģ¯
    0.07
    sing
    0.07
    mue
    0.07
    æĪijä¸Ģå®ļè¦ģ
    0.07
    Activations Density 0.003%

    No Known Activations