© 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. 23272
    Prev
    Next
    INDEX
    Explanations

    mediator, decay, half, cuff

    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
    æľŁåĪĿ
    -0.09
    æľ¬æĹ¥
    -0.08
    è¾¹è§Ĵ
    -0.08
    åĽ¾æºIJ
    -0.07
    ç·£
    -0.07
    anggil
    -0.07
    åİŁæĸĩéĵ¾æİ¥
    -0.07
     odw
    -0.07
     Marino
    -0.07
    æij©æł¹
    -0.07
    POSITIVE LOGITS
    ä»ĭ
    0.10
    mid
    0.10
    ä½įç½®
    0.09
     mid
    0.08
     middle
    0.08
     position
    0.08
     midway
    0.08
    position
    0.08
    离
    0.08
    ä½įç½®çļĦ
    0.07
    Activations Density 0.005%

    No Known Activations