© 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. 61669
    Prev
    Next
    INDEX
    Explanations

    adult content and protected information

    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
    zlich
    -0.07
    æľĢåIJİçĻ»å½ķ
    -0.07
    Checked
    -0.07
    éĢĻæĺ¯
    -0.07
     TypeInfo
    -0.07
    colari
    -0.07
    æĻķ
    -0.07
    æĦ
    -0.07
    >Lorem
    -0.07
    mond
    -0.06
    POSITIVE LOGITS
    bacher
    0.08
    zyb
    0.07
    é¢ł
    0.07
    rium
    0.06
    opak
    0.06
    çļĦ人è¿ĺ
    0.06
    赶å¿Ļ
    0.06
    opic
    0.06
    istre
    0.06
    æķ£çļĦ
    0.06
    Activations Density 0.513%

    No Known Activations