© 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. 20819
    Prev
    Next
    INDEX
    Explanations

    low temperatures and cryogenic conditions

    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
    è¸ıéĿĴ
    -0.08
    èĢĺ
    -0.08
    å«ī
    -0.07
    èī³éĺ³
    -0.07
    å±ħæĺĵ
    -0.07
    ORIZ
    -0.07
    鼨åŃ£
    -0.07
    åĪĩç£ĭ
    -0.07
    ä¸Ń庸
    -0.06
    ç«ŀ
    -0.06
    POSITIVE LOGITS
    ä½İ温
    0.11
     cold
    0.11
     colder
    0.11
    åĨ·çļĦ
    0.11
    åĨ·
    0.10
    cold
    0.10
     lạnh
    0.10
     temperatures
    0.10
    鼶ä¸ĭ
    0.10
     cry
    0.10
    Activations Density 0.021%

    No Known Activations