© 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. 21850
    Prev
    Next
    INDEX
    Explanations

    works in

    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
    éģĤ
    -0.07
    _wr
    -0.07
     sm
    -0.07
    _encoding
    -0.06
    /LICENSE
    -0.06
    gado
    -0.06
    æIJĵ
    -0.06
    åıijå±ķæĪIJ为
    -0.06
    诲
    -0.06
    ttl
    -0.06
    POSITIVE LOGITS
    åĽºçĦ¶
    0.09
    ä½łåħĪ
    0.09
    ãģ¾ãģļ
    0.09
    aksin
    0.08
     sekaligus
    0.08
    ä¹Łå¥½
    0.08
    nga
    0.08
     Ø£ÙĪÙĦا
    0.07
    ä¸Ģæĸ¹éĿ¢
    0.07
     primero
    0.07
    Activations Density 0.309%

    No Known Activations