© 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. 20536
    Prev
    Next
    INDEX
    Explanations

    incandescent bulb filament 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
    igsaw
    -0.08
    klar
    -0.07
     Leite
    -0.07
     Laf
    -0.07
    éĽĨä¸Ńæķ´æ²»
    -0.07
    ä¸İæĪij
    -0.07
    _NATIVE
    -0.06
     rabat
    -0.06
    Stack
    -0.06
    æ¸ħçĪ½
    -0.06
    POSITIVE LOGITS
     hotter
    0.09
    intern
    0.09
     bulb
    0.09
    éĩijå¥ĸ
    0.09
     heating
    0.09
     temperatures
    0.08
    åĬłçĥŃ
    0.08
    é«ĺ温
    0.08
    çļĦé«ĺ温
    0.08
     nóng
    0.08
    Activations Density 0.023%

    No Known Activations