© 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. 49976
    Prev
    Next
    INDEX
    Explanations

    SAR studies

    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
    subs
    -0.07
    æ»ĭ
    -0.07
    æŃ£å¸¸çļĦ
    -0.06
    å®ĥæīĢ
    -0.06
     Conserv
    -0.06
     Comple
    -0.06
    åħ¨ä½ĵ人åijĺ
    -0.06
     perpet
    -0.06
    arach
    -0.06
     everyday
    -0.06
    POSITIVE LOGITS
    æ·»åĬł
    0.09
    修饰
    0.09
     synerg
    0.09
     incorporation
    0.09
     destabil
    0.09
    modifier
    0.08
    çµĦåIJĪ
    0.08
     gezielt
    0.08
    æĿIJæĸĻåıĬ
    0.08
    åı¯ä»¥æĶ¹åĸĦ
    0.08
    Activations Density 0.112%

    No Known Activations