© 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. 37429
    Prev
    Next
    INDEX
    Explanations

    memoir or young person

    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
    åĨĻæĻ¯
    -0.07
    çĸ
    -0.06
    Äħ
    -0.06
    ung
    -0.06
    æķ´ä¸ªéĹ®é¢ĺ
    -0.06
    女åŃIJçļĦ
    -0.06
    ong
    -0.06
    çľ¼çľĭ
    -0.06
    âĢij
    -0.06
    æ¡IJ
    -0.06
    POSITIVE LOGITS
    æľĢæĸ°è¯Ħ论
    0.09
    ä¸ºä½łæݨèįIJ
    0.08
    usher
    0.08
    çĴĢ
    0.08
    SEE
    0.08
    erja
    0.07
    éĶ¦æłĩ
    0.07
    trys
    0.07
    schn
    0.07
    åĨįçĤ¹åĩ»
    0.07
    Activations Density 0.840%

    No Known Activations