© 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. 33748
    Prev
    Next
    INDEX
    Explanations

    temperature meter

    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
    å°ıå²Ľ
    -0.07
    å°ĨæīĢæľī
    -0.07
    iak
    -0.07
    æĹłè¾¹
    -0.07
    åŁºæľ¬æĬĢèĥ½
    -0.06
    etwork
    -0.06
    æľ¬ç½ij
    -0.06
    odle
    -0.06
    mtree
    -0.06
    adelphia
    -0.06
    POSITIVE LOGITS
    对人类
    0.09
    竺
    0.08
     Wien
    0.08
    åIJī祥
    0.07
     thermometer
    0.07
    ново
    0.07
    温度计
    0.07
     thermal
    0.07
     alp
    0.07
    uja
    0.07
    Activations Density 0.001%

    No Known Activations