© 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. 34708
    Prev
    Next
    INDEX
    Explanations

    aid the French resistance

    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
    就已ç»ı
    -0.08
    à¸ĩ
    -0.08
    å°±åĥıæĺ¯
    -0.07
    æ¯Ķå¦Ĥ说
    -0.07
    éĺħè¯»æľ¬æĸĩ
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    åºĶ该æĺ¯
    -0.07
    åºĶ该æĢİä¹Ī
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    è¿Ļ件äºĭæĥħ
    -0.07
    POSITIVE LOGITS
    éľĢåľ¨
    0.11
    éľĢçĶ¨
    0.11
    çŁ¥çļĦ
    0.11
    ลฯ
    0.10
    ä½ķåľ°
    0.10
    äºİä¸Ģ
    0.10
    çĦ¶å¤§
    0.10
    çĦ¶æĺ¯
    0.10
    æķĻäºİ
    0.10
    éľĢ
    0.10
    Activations Density 0.096%

    No Known Activations