© 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. 7149
    Prev
    Next
    INDEX
    Explanations

    why certain things are importance

    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
    å¤ļå°ij
    -0.07
    akh
    -0.07
     Wolfs
    -0.07
     évidemment
    -0.07
    ãģ§ãģĻãģĭãĤī
    -0.07
     collabor
    -0.07
    å°Ķé¡¿
    -0.06
    åħĭæĸ¯åĿ¦
    -0.06
    ãĥĥãĤ«ãĥ¼
    -0.06
    zal
    -0.06
    POSITIVE LOGITS
     padahal
    0.09
    éģĵéķ¿
    0.09
     despite
    0.08
    èĢĮä¸įæĺ¯
    0.08
    äºĨåij¢
    0.08
    é«ĺçħ§
    0.08
     nonostante
    0.08
    ?>>
    0.08
     ÙĪØ£ÙĨÙĩ
    0.08
     whereas
    0.07
    Activations Density 0.087%

    No Known Activations