© 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. 20213
    Prev
    Next
    INDEX
    Explanations

    measuring instruments and devices

    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
    ä¸įæĹ©
    -0.09
    ourt
    -0.08
     pétr
    -0.08
    лле
    -0.07
    ÑĢоÑı
    -0.07
     autogenerated
    -0.07
    软硬
    -0.07
    illow
    -0.07
     génération
    -0.07
    ipel
    -0.07
    POSITIVE LOGITS
    éĩıç¨ĭ
    0.11
    æµĭéĩı
    0.08
     measuring
    0.08
     Precision
    0.08
    åĪ»åº¦
    0.08
     precision
    0.07
    æĶ¹è£ħ
    0.07
    æ»¨æ±Ł
    0.07
    æݥ线
    0.07
     겸
    0.07
    Activations Density 0.001%

    No Known Activations