© 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. 62548
    Prev
    Next
    INDEX
    Explanations

    heating and air conditioning systems

    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
    éĢłèĪ¹
    -0.08
    箸
    -0.07
    éĻĮ
    -0.07
    ÐijÐł
    -0.07
    BUM
    -0.07
    渡åı£
    -0.07
    éĹªåħīçģ¯
    -0.07
    é£Łåĵģæ·»åĬłåīĤ
    -0.07
    æĺ¾å¾®
    -0.06
    æīĵçģ«æľº
    -0.06
    POSITIVE LOGITS
    空è°ĥ
    0.12
     HVAC
    0.11
     thermostat
    0.11
    ä¸Ń央空è°ĥ
    0.09
     thrott
    0.09
     airflow
    0.09
    åĨ·æļĸ
    0.09
     cozy
    0.09
    å·¥åĨµ
    0.09
    æļĸ
    0.09
    Activations Density 0.164%

    No Known Activations