© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44666
    Prev
    Next
    INDEX
    Explanations

    endings and beginnings

    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
    Negative Logits
    agam
    -0.08
    éļĶ天
    -0.08
    _ISR
    -0.08
    åįĥæĸ¹
    -0.08
    å½ĵåľ°çļĦ
    -0.07
    åľ¨è§Ħå®ļ
    -0.07
    å¾ĹçŁ¥
    -0.07
    åľ¨å½ĵæŶ
    -0.07
    preter
    -0.07
    åľ¨å½ĵåľ°
    -0.07
    POSITIVE LOGITS
    æĪij们æŃ£åľ¨
    0.11
     unprecedented
    0.11
    æ¯Ķåݻ年
    0.09
    缮åīįæŃ£åľ¨
    0.09
    æĸ°æł¼å±Ģ
    0.09
     accelerating
    0.09
    缮åīįæĺ¯
    0.09
    åīįæīĢæľªæľīçļĦ
    0.08
     global
    0.08
    å¹´åħ¨çIJĥ
    0.08
    Activations Density 0.945%

    No Known Activations