© 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. 9767
    Prev
    Next
    INDEX
    Explanations

    initials

    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
    resco
    -0.08
    æ¯ıåIJį
    -0.08
    è¿ijå¹³
    -0.07
    çĵ¦å°Ķ
    -0.07
    çĥŃéŨæݨèįIJ
    -0.07
    åı¯ä»¥ä¿Ŀè¯ģ
    -0.07
    agnar
    -0.07
    網
    -0.07
    åĪ·
    -0.07
    eba
    -0.07
    POSITIVE LOGITS
     rearr
    0.10
    åģıæĹģ
    0.09
    agram
    0.08
    æĭ¼
    0.08
    åŃĹå½¢
    0.08
    éĥ¨é¦ĸ
    0.07
    iskey
    0.07
    æĭ¼æİ¥
    0.07
    æİĴåĪĹ
    0.07
    agrams
    0.06
    Activations Density 0.001%

    No Known Activations