© 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. 33793
    Prev
    Next
    INDEX
    Explanations

    impulse, pulse, flash, click, discharge, currents

    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
    æĹ¥æ¸IJ
    -0.09
    è°Ĩ
    -0.08
    è¶Ĭèµ°è¶Ĭ
    -0.08
    ãĤĴéĢ²
    -0.08
    èĢ
    -0.08
    æ¸IJæ¸IJ
    -0.07
    éĿ¡
    -0.07
     steadily
    -0.07
    èĭ¦æģ¼
    -0.07
    éĢIJæ¸IJæĪIJ为
    -0.07
    POSITIVE LOGITS
    çŀ¬éĹ´
    0.14
    çŀ¬æŶ
    0.13
    Occurred
    0.12
    çļĦçŀ¬éĹ´
    0.12
    çŁŃæļĤçļĦ
    0.12
    çŁŃæļĤ
    0.12
    çĪĨåıij
    0.12
     instantaneous
    0.12
     burst
    0.12
    çĪĨåıijçļĦ
    0.12
    Activations Density 0.480%

    No Known Activations