© 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. 32335
    Prev
    Next
    INDEX
    Explanations

    programming code constructs

    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
    itia
    -0.07
     Mati
    -0.07
    è¿Ļ个社ä¼ļ
    -0.07
    istrate
    -0.07
    CLU
    -0.07
    åĬ¨èĦī硬åĮĸ
    -0.07
    ä¹Łæľīä¸Ģå®ļçļĦ
    -0.07
    åħ¬åı¸ç®Ģä»ĭ
    -0.07
    ÙıÙĪÙĨ
    -0.07
    ible
    -0.06
    POSITIVE LOGITS
    ä¸ĭ
    0.07
    TagName
    0.07
    ormal
    0.07
    豫
    0.07
    ulist
    0.06
    izu
    0.06
    uby
    0.06
    มิà¸ķร
    0.06
    icks
    0.06
    —with
    0.06
    Activations Density 0.002%

    No Known Activations