© 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. 23568
    Prev
    Next
    INDEX
    Explanations

    pulse timing and repetition

    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¸įäºĨäºĨ
    -0.07
    mob
    -0.07
    åĤ¬åĮĸ
    -0.07
    Mob
    -0.06
    KM
    -0.06
    æĽ²éĿ¢
    -0.06
    ä¿ĿæĬ¤å±Ĥ
    -0.06
    毡
    -0.06
    æ°´åľŁ
    -0.06
    åĸ«
    -0.06
    POSITIVE LOGITS
     timed
    0.11
    odic
    0.10
     intermitt
    0.10
    secutive
    0.09
     dwell
    0.09
     waveform
    0.09
     bursts
    0.09
    éĹ´éļĶ
    0.09
     timing
    0.09
    è¿ŀç»ŃçļĦ
    0.09
    Activations Density 0.152%

    No Known Activations