© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29912
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases or noun phrases

    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
    꽤
    -0.08
    upra
    -0.08
    ilton
    -0.07
    ä¸įåħħåĪĨ
    -0.07
     concept
    -0.07
    êµīìŀ¥
    -0.07
    æĹłæ³ķ满足
    -0.07
    atu
    -0.07
    æ¦Ĥ念
    -0.06
     indirectly
    -0.06
    POSITIVE LOGITS
    ä¸į带
    0.08
    æĸĩä»¶æł¼å¼ı
    0.07
    _drv
    0.07
    带ä¸Ĭ
    0.07
    è¢
    0.07
     commas
    0.07
    çķ¥å¸¦
    0.07
     ìłķíĻķíķľ
    0.07
    æĭ¬
    0.07
     slight
    0.07
    Activations Density 0.031%

    No Known Activations