© 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. 1437
    Prev
    Next
    INDEX
    Explanations

    formula for sum or fraction

    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
    ë§Į
    -0.07
     اÙĦÙģا
    -0.07
    å¨ħ
    -0.07
    schw
    -0.07
    cket
    -0.07
    .fm
    -0.07
    åIJĽçļĦ
    -0.07
    ibra
    -0.07
    ä¹±äºĨ
    -0.07
    人çļĦçĶŁåij½
    -0.06
    POSITIVE LOGITS
    è¶ĭåIJij
    0.07
     prob
    0.07
    orney
    0.07
    iega
    0.07
    aisia
    0.07
    YO
    0.06
    oine
    0.06
    ÑģÑĤва
    0.06
    YE
    0.06
    空åīį
    0.06
    Activations Density 0.019%

    No Known Activations