© 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. 44822
    Prev
    Next
    INDEX
    Explanations

    numbers and other languages

    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
    igny
    -0.08
    éĢļè¿ĩçĶµè¯Ŀ
    -0.07
    æĶ¶èĹıæľ¬ç«Ļ
    -0.07
    opers
    -0.07
    æ¸ĹéĢı
    -0.07
    ä¹Łè¢«ç§°ä¸º
    -0.07
    Ferr
    -0.07
     dearly
    -0.07
    pell
    -0.06
    ç±³åħ°
    -0.06
    POSITIVE LOGITS
    ally
    0.07
    æľĪåŃIJ
    0.07
    æīĢåģļ
    0.07
    laki
    0.07
    æĹłç¼ĺ
    0.06
    æĪij便
    0.06
    çĶ¨æĪ·ä½¿çĶ¨
    0.06
    便ä¼ļ
    0.06
    å·¥ä½ľåıĬ
    0.06
    ä½ľåĪĻ
    0.06
    Activations Density 0.001%

    No Known Activations