© 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. 16955
    Prev
    Next
    INDEX
    Explanations

    first item / last item

    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
    ahari
    -0.07
    åı¦ä¸Ģ
    -0.07
    öhn
    -0.06
    æĽ¦
    -0.06
    æĢ§åľ°
    -0.06
    äºĮåŃĹ
    -0.06
    Ä©a
    -0.06
    åIJĮä¸Ģ
    -0.06
     themselves
    -0.06
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.06
    POSITIVE LOGITS
    (s
    0.12
    åĴĮæľĢ
    0.10
    æĪĸå¤ļ个
    0.10
    ä¹Łæĺ¯æľĢ
    0.09
    æĪĸå¤ļ
    0.09
    à¦Łà¦¿à¦°
    0.08
     saja
    0.08
     ÙĪØ£Ùĥثر
    0.08
    cula
    0.07
     ooit
    0.07
    Activations Density 0.096%

    No Known Activations