© 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. 19616
    Prev
    Next
    INDEX
    Explanations

    cooling and solidification processes

    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
    æľºåħ³
    -0.08
    ç»ĪæĹ¥
    -0.07
    éķ¿éĿĴ
    -0.07
    à¸Ħล
    -0.07
     corro
    -0.06
    -serving
    -0.06
    è¦ģç»ı常
    -0.06
     quarterly
    -0.06
     recurring
    -0.06
    oday
    -0.06
    POSITIVE LOGITS
     cooling
    0.12
    éĻį温
    0.11
     cooled
    0.10
    åĨ·åį´
    0.10
     Cooling
    0.10
    Cool
    0.09
     temperatures
    0.09
    æĿ¥ä¸įåıĬ
    0.09
     thermal
    0.09
    cool
    0.09
    Activations Density 0.011%

    No Known Activations