© 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. 17976
    Prev
    Next
    INDEX
    Explanations

    real-space / real-time

    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
     polys
    -0.08
     Purs
    -0.07
    è¿«
    -0.07
    rek
    -0.07
    Ó¯
    -0.06
    çľ¼çĿģ
    -0.06
     %-
    -0.06
     Motel
    -0.06
    å®īåħ¨ä¿Ŀéļľ
    -0.06
    urit
    -0.06
    POSITIVE LOGITS
    -local
    0.09
     localize
    0.09
     locality
    0.08
    local
    0.08
     localization
    0.08
     локали
    0.08
     Localization
    0.08
    æł¼æĸ¯
    0.08
    localized
    0.08
    è¿ijè·Ŀ离
    0.08
    Activations Density 0.003%

    No Known Activations