© 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. 49715
    Prev
    Next
    INDEX
    Explanations

    arterial

    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
    å¾ĢæľŁç²¾å½©
    -0.07
    æĪĸåĪłéĻ¤
    -0.07
    loe
    -0.07
    ordon
    -0.07
    å®ļçļĦ
    -0.07
    éĩĪ
    -0.07
    èħ»
    -0.06
    erman
    -0.06
    å¸ļ
    -0.06
    åĴĮä½ľçĶ¨
    -0.06
    POSITIVE LOGITS
    ç²¥æł·
    0.11
    ialis
    0.09
    eka
    0.08
    ousel
    0.08
    ousy
    0.08
    æºIJæĢ§
    0.08
    ekom
    0.08
    ysten
    0.08
    Ïģεί
    0.08
    aments
    0.08
    Activations Density 0.062%

    No Known Activations