© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61748
    Prev
    Next
    INDEX
    Explanations

    lung function tests, complications, decades, time, minutes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĪĸèĢħåħ¶ä»ĸ
    -0.10
    以åıĬåħ¶ä»ĸ
    -0.08
    æĪĸèĢħæĺ¯
    -0.08
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.08
    **–
    -0.08
    æĪĸåħ¶ä»ĸ
    -0.08
    atau
    -0.08
    æĪĸèĢħ
    -0.08
     ataupun
    -0.07
    æĪĸèĢħ说
    -0.07
    POSITIVE LOGITS
     whereas
    0.08
     anyway
    0.08
    åIJĦæĹı
    0.07
    ×Ļ×ĵ
    0.07
     appunto
    0.07
    èĢĮè¡Į
    0.07
    åĨį说äºĨ
    0.07
     unlike
    0.07
     rather
    0.06
     Whereas
    0.06
    Activations Density 0.083%

    No Known Activations