© 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. 10927
    Prev
    Next
    INDEX
    Explanations

    heat transfer and loss

    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
     EMPTY
    -0.07
    箩
    -0.07
    acam
    -0.07
    ouncy
    -0.07
    åıĹç²¾
    -0.07
    ÑĨенÑĤÑĢи
    -0.07
     "@"
    -0.07
     emas
    -0.06
    åįĬæķ°
    -0.06
     ÑĢÑı
    -0.06
    POSITIVE LOGITS
     heat
    0.15
     thermal
    0.14
     Heat
    0.13
    çĥŃ
    0.13
    heat
    0.12
     Thermal
    0.12
    çĨ±
    0.12
    Heat
    0.12
    thermal
    0.12
    çĥŃéĩı
    0.12
    Activations Density 0.023%

    No Known Activations