© 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. 39955
    Prev
    Next
    INDEX
    Explanations

    distance metric

    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
     tall
    -0.08
    é«ĺçĥŃ
    -0.07
    isial
    -0.07
    esel
    -0.07
    laus
    -0.07
    年满
    -0.07
    ãĤµãĤ¯
    -0.07
    etos
    -0.07
    天èĬ±
    -0.07
    боÑĢе
    -0.07
    POSITIVE LOGITS
     distance
    0.10
    çļĦè·Ŀ离
    0.10
     distances
    0.09
    è·ĿéĽ¢
    0.09
    erro
    0.09
    èī²å·®
    0.09
    è·Ŀ离
    0.09
    Distance
    0.09
    å·´å·´
    0.09
    distance
    0.08
    Activations Density 0.011%

    No Known Activations