© 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. 7203
    Prev
    Next
    INDEX
    Explanations

    correctly wired objects

    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
    æĽ´ä½³
    -0.07
    ãģĤãĤĭãģĦãģ¯
    -0.07
    éĻĦè¿ij
    -0.07
    æľªå¿ħ
    -0.06
    å¾Ģå¾Ģ
    -0.06
    éĢļ常
    -0.06
    ãĤĤãģĹãģıãģ¯
    -0.06
    ä½Ĩæĺ¯ä¸Ģ
    -0.06
     foremost
    -0.06
    å¾Īä¸į
    -0.06
    POSITIVE LOGITS
    ä¸ĵäººè´Łè´£
    0.09
    没æľīéĹ®é¢ĺ
    0.09
    éĢ»è¾ij
    0.08
    ToObject
    0.08
    没æľīåľ¨
    0.08
    没æľīåĩºçİ°
    0.08
    .pg
    0.08
     correctly
    0.08
    æĹłè¯¯
    0.08
    _NOP
    0.07
    Activations Density 0.003%

    No Known Activations