© 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. 48767
    Prev
    Next
    INDEX
    Explanations

    quantum physics and temperature

    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
    æĸ°ç¤¾
    -0.07
    egy
    -0.07
    IGGER
    -0.07
    egu
    -0.07
    igas
    -0.07
    æĸ°æľĪ
    -0.07
    ÑģоÑĢ
    -0.07
    chine
    -0.07
    说罢
    -0.06
    _alg
    -0.06
    POSITIVE LOGITS
    éļĶ
    0.08
     freezing
    0.08
    åĨ»ç»ĵ
    0.08
    à¥ģà¤ķ
    0.07
    è°±
    0.07
     falle
    0.07
     temperatures
    0.07
    段æŶéĹ´
    0.07
     freezes
    0.07
    ä½İ温
    0.07
    Activations Density 0.004%

    No Known Activations