© 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. 63794
    Prev
    Next
    INDEX
    Explanations

    power grid and electricity schedules

    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
     NIH
    -0.07
    chnik
    -0.07
     extrad
    -0.07
    çī©è³ª
    -0.07
     attachment
    -0.07
    代çIJĨæľīéĻIJåħ¬åı¸
    -0.07
    æī«æıı
    -0.06
    åĪ¶åĵģ
    -0.06
     scaffold
    -0.06
    ansch
    -0.06
    POSITIVE LOGITS
    è°ĥ度
    0.10
     surplus
    0.09
     electricity
    0.09
    æİ¥åħ¥
    0.09
    åīĬ
    0.09
    è´Łèį·
    0.09
    -load
    0.09
     tariffs
    0.09
     kWh
    0.09
     tariff
    0.09
    Activations Density 0.054%

    No Known Activations