© 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. 49442
    Prev
    Next
    INDEX
    Explanations

    calibrate, DPI, unit, ratio

    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
    ç»´
    -0.07
    æĬĽ
    -0.07
    追尾
    -0.07
    assen
    -0.07
    GLE
    -0.07
    è¿ijä¹İ
    -0.07
     vár
    -0.07
    讨
    -0.07
     Claus
    -0.07
    igroup
    -0.07
    POSITIVE LOGITS
    å°º
    0.10
     calibration
    0.08
     stretch
    0.08
     calibrated
    0.08
    æĶ¾å¤§
    0.07
     converter
    0.07
    åĪ»åº¦
    0.07
    rup
    0.07
     Calibration
    0.07
    ä¸İå®ŀéĻħ
    0.07
    Activations Density 0.011%

    No Known Activations