© 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. 55086
    Prev
    Next
    INDEX
    Explanations

    have a

    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
    æĴĩ
    -0.07
    pis
    -0.07
    pit
    -0.06
    Õ¸ÖĤÕ¶
    -0.06
    èĭ¥æĹł
    -0.06
     pit
    -0.06
    å·§
    -0.06
    æĺ¯æĢİæł·çļĦ
    -0.06
     thereof
    -0.06
    å®ĺæĸ¹åįļ客
    -0.06
    POSITIVE LOGITS
    Ø«ÙĪر
    0.10
    ÑĦе
    0.09
     urgente
    0.09
     ÑħоÑĩÑĥ
    0.08
    æĹ¥åĪ¶
    0.08
    yj
    0.08
    éĥ½ä¸į太
    0.08
    å¾ģéĢĶ
    0.08
    æĥ³äºĨ解
    0.08
    rawer
    0.08
    Activations Density 0.210%

    No Known Activations