© 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. 18811
    Prev
    Next
    INDEX
    Explanations

    worst case

    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
    à¹ī
    -0.10
    zkod
    -0.09
    ä¸įå½Ĵ
    -0.09
    ToSelector
    -0.09
    ToWorld
    -0.09
    /videos
    -0.09
    trs
    -0.09
    spflicht
    -0.09
    gypt
    -0.09
    ÙĪسÛĮ
    -0.08
    POSITIVE LOGITS
    -case
    0.13
    æĥħåĨµä¸ĭ
    0.08
    ablish
    0.07
    /un
    0.06
    imal
    0.06
    /
    0.06
    ening
    0.06
    imum
    0.06
    -
    0.06
    Äģk
    0.06
    Activations Density 0.006%

    No Known Activations