© 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. 6963
    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
    åħ·æľī以ä¸ĭ
    -0.07
    Nevertheless
    -0.07
    æľīä¸ĭåĪĹ
    -0.07
     Accordingly
    -0.07
     ...
    -0.07
     âĢ¦
    -0.07
     Nevertheless
    -0.06
     Nonetheless
    -0.06
    尽管å¦ĤæѤ
    -0.06
     “
    -0.06
    POSITIVE LOGITS
    è¿ĺæľīåĵªäºĽ
    0.09
    ighter
    0.09
     definitely
    0.08
     мол
    0.08
    è¿Ļæĺ¯ä¸ª
    0.08
    æ¯Ķå¦Ĥ
    0.08
    Ń
    0.08
     maybe
    0.08
    è¿ĺæľī个
    0.08
    tia
    0.08
    Activations Density 0.000%

    No Known Activations