© 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. 34904
    Prev
    Next
    INDEX
    Explanations

    redefine, transform, revolutionize

    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
    çļĦå¢ŀåĬł
    -0.07
    ä¸įæĸŃå¢ŀéķ¿
    -0.07
    uned
    -0.07
    anima
    -0.07
    ä¸įç»Ŀ
    -0.06
     coff
    -0.06
    warts
    -0.06
    ä¹ĭä¸į
    -0.06
     accumul
    -0.06
    ä¸įå¿ĺ
    -0.06
    POSITIVE LOGITS
     radically
    0.14
    以éĢĤåºĶ
    0.13
    æĶ¹åıĺäºĨ
    0.13
    æĶ¹åıĺ
    0.13
     changed
    0.12
    åİŁæĿ¥çļĦ
    0.11
    åıĺéĿ©
    0.11
    ä¸ĢæĶ¹
    0.11
    æĶ¹è®Ĭ
    0.11
    æĶ¹åıĺçļĦ
    0.11
    Activations Density 0.263%

    No Known Activations