© 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. 7130
    Prev
    Next
    INDEX
    Explanations

    works fine or correctly

    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
    ennon
    -0.08
    etta
    -0.08
    ugged
    -0.08
    çĽ¸ä¿¡åľ¨
    -0.07
    etch
    -0.07
    ylie
    -0.07
     Lans
    -0.07
    ä¿¡æģ¯çŃī
    -0.07
    anguage
    -0.07
    snd
    -0.07
    POSITIVE LOGITS
    ä½ĨéļıçĿĢ
    0.09
     pass
    0.08
    .Then
    0.07
     Meanwhile
    0.07
    å°±ç®ĹäºĨ
    0.06
    æĶ¶
    0.06
    ä¸İæѤåIJĮæŶ
    0.06
    ä¼ĺçĤ¹æĺ¯
    0.06
    èĢĮå½ĵ
    0.06
    åı¦ä¸Ģæĸ¹éĿ¢
    0.06
    Activations Density 0.127%

    No Known Activations