© 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. 11493
    Prev
    Next
    INDEX
    Explanations

    timing of events

    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
    icular
    -0.08
    æĸ°å±ĢéĿ¢
    -0.07
    omia
    -0.07
     dauerhaft
    -0.06
    æºIJè¿ľæµģ
    -0.06
    è¯ģ件类åŀĭ
    -0.06
    å¹´æĸ°
    -0.06
    xt
    -0.06
    iz
    -0.06
    iales
    -0.06
    POSITIVE LOGITS
     timing
    0.11
    timing
    0.10
    Timing
    0.10
    åĴĮåĨħ容
    0.10
     Timing
    0.09
    æĹ¶æľº
    0.09
     kapan
    0.09
    ãĤ¿ãĤ¤ãĥŁãĥ³ãĤ°
    0.09
    å®īæİĴçļĦ
    0.09
     ë§ŀì¶Ķ
    0.09
    Activations Density 0.101%

    No Known Activations