© 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. 22613
    Prev
    Next
    INDEX
    Explanations

    combustion gas, well to, sorting facilities, Ajax request, bleach-fix, spray unit

    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
     got
    -0.07
     (
    -0.07
    ·
    -0.06
    æģ¶
    -0.06
     compiled
    -0.06
    ,
    -0.06
    -0.06
    é¢Ħéĺ²ä¸ºä¸»
    -0.06
    .
    -0.06
    got
    -0.06
    POSITIVE LOGITS
    ANDLE
    0.09
    å¤ĦçIJĨåIJİ
    0.09
    æݨèįIJæ¦ľ
    0.09
    æĪIJåĬŁåIJİ
    0.09
     بعدÙħا
    0.09
    zada
    0.09
     пÑĸÑģлÑı
    0.09
    åIJİ继
    0.08
    Ïĩο
    0.08
    дие
    0.08
    Activations Density 0.032%

    No Known Activations