© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55463
    Prev
    Next
    INDEX
    Explanations

    abstract:

    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
    ä»ĸåį´
    -0.07
    峨
    -0.07
     Hidalgo
    -0.06
    ç£¨çłº
    -0.06
    ίδ
    -0.06
    æ³¥
    -0.06
     naughty
    -0.06
    ä»ĸä¹Ł
    -0.06
     he
    -0.06
    èĤ
    -0.06
    POSITIVE LOGITS
    adie
    0.08
    ãĤ¢ãĤ·
    0.08
    iasi
    0.07
    ä¸ĢæıIJ
    0.07
    anggan
    0.07
    isht
    0.07
    éĢļè¿ĩå°Ĩ
    0.07
    æĸ°è¦ı
    0.07
    angkan
    0.07
    åľ°æľĽçĿĢ
    0.07
    Activations Density 0.013%

    No Known Activations