© 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. 30211
    Prev
    Next
    INDEX
    Explanations

    rate and factors

    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
    éĿĴæĿ¾
    -0.08
    ?action
    -0.08
    antar
    -0.08
    éķ¿æĮīäºĮç»´çłģ
    -0.08
    onet
    -0.07
    antis
    -0.07
    baran
    -0.07
    imb
    -0.07
    åŃ¢
    -0.07
    itten
    -0.07
    POSITIVE LOGITS
    ä¹Łè·ŁçĿĢ
    0.11
    ä¹Łéļıä¹ĭ
    0.11
    缸åºĶçļĦ
    0.11
    缸åºĶ
    0.11
    éļıä¹ĭ
    0.11
    åIJĮæĹ¶ä¹Ł
    0.10
    ä½ĨåIJĮæŶ
    0.10
    åIJĮæŃ¥
    0.09
    è·ŁçĿĢ
    0.09
     simultaneously
    0.09
    Activations Density 0.071%

    No Known Activations