© 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. 37661
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ade
    -0.08
    èĩªå·±çļĦæĥ³æ³ķ
    -0.08
    éĴĿ
    -0.07
     revend
    -0.06
     dull
    -0.06
     prof
    -0.06
     seme
    -0.06
     claimed
    -0.06
    nish
    -0.06
    Ñĩик
    -0.06
    POSITIVE LOGITS
    ariam
    0.07
    èĬ±ä¸Ģ
    0.07
    æĹłæķĮ
    0.07
    ejo
    0.07
    åĺ
    0.07
    alti
    0.07
    è¬Ľ
    0.07
    夫æĸ¯åŁº
    0.07
    rato
    0.07
    å¸Ĥåľºåıijå±ķ
    0.07
    Activations Density 0.000%

    No Known Activations