© 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. 56796
    Prev
    Next
    INDEX
    Explanations

    inference rules, logical operators, mathematical comparisons

    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
    ¼
    -0.06
    -0.06
    hesive
    -0.06
    幸
    -0.06
     pol
    -0.06
    hung
    -0.06
    计åħ¥
    -0.06
     accommodating
    -0.05
     improvis
    -0.05
    åĪ©æĸ¯
    -0.05
    POSITIVE LOGITS
    è¯ģ
    0.09
    ä¸ĩåı¤
    0.08
     stadion
    0.08
    第äºĮæĿ¡
    0.08
    鸳
    0.08
     ÑģодеÑĢж
    0.08
     пакеÑĤ
    0.08
    è¯ģçļĦ
    0.08
    æݨçIJĨ
    0.08
     assertNotNull
    0.08
    Activations Density 0.002%

    No Known Activations