© 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. 15876
    Prev
    Next
    INDEX
    Explanations

    UUIDs and identifiers

    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
    ysel
    -0.08
    Unnamed
    -0.08
    ulum
    -0.07
    tuu
    -0.07
    étr
    -0.07
    idade
    -0.07
    ä¹İ
    -0.07
    tron
    -0.07
    mata
    -0.07
    æĺ¯ä½łçļĦ
    -0.07
    POSITIVE LOGITS
    åĨ¤
    0.07
    ÙĪاب
    0.07
    ä¹ĭçľ¼
    0.07
     Thừa
    0.07
    acle
    0.06
     Williamson
    0.06
    ä¹ĭ梦
    0.06
    erenc
    0.06
    OLVE
    0.06
    人åĥı
    0.06
    Activations Density 0.069%

    No Known Activations