© 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. 61427
    Prev
    Next
    INDEX
    Explanations

    time differences

    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
    arre
    -0.07
    emme
    -0.06
    anka
    -0.06
    ени
    -0.06
    ัà¸ģษà¹Į
    -0.06
    áĢĻáĢºáĢ¸
    -0.06
    æĮijèµ·
    -0.06
    alba
    -0.06
    大麻
    -0.06
    AI
    -0.06
    POSITIVE LOGITS
    assed
    0.08
    adalafil
    0.08
    欢è¿İ访éĹ®
    0.08
    ä¾ĽåºĶ产åĵģ
    0.08
    encontre
    0.08
    ,top
    0.07
    以ä¸ĭæĺ¯å°ıç¼ĸ
    0.07
    ylim
    0.07
    pflan
    0.07
    åħĭæľįåĽ°éļ¾
    0.07
    Activations Density 0.060%

    No Known Activations