© 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. 7313
    Prev
    Next
    INDEX
    Explanations

    infrared radiation and thermal emission

    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
    entak
    -0.08
    chine
    -0.07
    ç½ĹéĤ£
    -0.07
    prit
    -0.07
    crate
    -0.06
    å¤ļæĥ³
    -0.06
    èĪİ
    -0.06
    ahoo
    -0.06
    æŧåĿĢ
    -0.06
    ä¸įåīį
    -0.06
    POSITIVE LOGITS
    frared
    0.12
    (IR
    0.09
     thermal
    0.08
    红å¤ĸ
    0.08
     Thermal
    0.08
    ÙħÙĪÙĦ
    0.08
    thermal
    0.08
     infrared
    0.08
    æµĭ温
    0.08
    红å¤ĸ线
    0.08
    Activations Density 0.027%

    No Known Activations