© 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. 8857
    Prev
    Next
    INDEX
    Explanations

    inside of

    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
    prot
    -0.07
    plot
    -0.07
    es
    -0.06
    éĤ¦
    -0.06
    def
    -0.06
    詹
    -0.06
    æĿ¿ä¸Ĭ
    -0.06
    /Library
    -0.06
    bare
    -0.06
     Hera
    -0.06
    POSITIVE LOGITS
    .today
    0.09
     بدÙĪرÙĩ
    0.08
    loff
    0.08
    åIJĦèĩªçļĦ
    0.08
    çŁ¥ä¹ĭ
    0.08
    0.08
    াà¦ķা
    0.08
    _picker
    0.07
    ä¸ŃçļĦæķ°æį®
    0.07
    ascal
    0.07
    Activations Density 0.015%

    No Known Activations