© 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. 21445
    Prev
    Next
    INDEX
    Explanations

    aims to

    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
    iest
    -0.08
    arium
    -0.07
    mitt
    -0.07
    oro
    -0.07
    }}{{
    -0.07
    ä¸İä¼łç»Ł
    -0.07
    heen
    -0.07
    ازÙĦ
    -0.07
    ìĵ¸
    -0.07
    ORTE
    -0.07
    POSITIVE LOGITS
    æĥħæ·±
    0.08
    ä¸Ķåľ¨
    0.07
    ä¸Ķ
    0.07
    ابÙĬØ©
    0.07
    ibs
    0.07
    ops
    0.07
    çļĦæĿ¡ä»¶ä¸ĭ
    0.07
    uš
    0.06
    unchecked
    0.06
    ullen
    0.06
    Activations Density 0.001%

    No Known Activations