© 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. 29528
    Prev
    Next
    INDEX
    Explanations

    delay

    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
    iales
    -0.08
    ording
    -0.08
    -sama
    -0.08
    niec
    -0.07
    ergestellt
    -0.07
    quirer
    -0.07
    ulet
    -0.07
    geschrieben
    -0.07
    tracts
    -0.07
    avanaugh
    -0.07
    POSITIVE LOGITS
    ä¸įåĨ³
    0.12
    ataire
    0.09
    äºĨ对
    0.09
    rence
    0.08
    å·²ä¹ħçļĦ
    0.07
    äºĨä¸ĢæŃ¥
    0.07
    ми
    0.07
    atamente
    0.07
    ataires
    0.07
    ä¸ĭæĿ¥çļĦ
    0.07
    Activations Density 0.027%

    No Known Activations