© 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. 56091
    Prev
    Next
    INDEX
    Explanations

    conformal metrics, constraint equation, lapse

    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
    Union
    -0.07
    å¸Ńä½į
    -0.07
     pint
    -0.07
     inputs
    -0.06
     Union
    -0.06
     ...
    -0.06
    æ´»çļĦ
    -0.06
    èĮ¶æ°´
    -0.06
     plain
    -0.06
     arro
    -0.06
    POSITIVE LOGITS
    /stretch
    0.09
     locally
    0.08
    retch
    0.08
    obody
    0.08
    ettings
    0.08
    ewriter
    0.08
    spro
    0.08
    etrics
    0.08
    ometown
    0.07
    _metric
    0.07
    Activations Density 0.004%

    No Known Activations