© 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. 13640
    Prev
    Next
    INDEX
    Explanations

    Mounds Candy Bar, Beverly Jenkins

    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
    åĬĽå£«
    -0.08
    جاÙħ
    -0.08
    注æĦıçļĦæĺ¯
    -0.08
    assi
    -0.07
    tex
    -0.07
    ANH
    -0.07
    mist
    -0.07
    epass
    -0.07
    auta
    -0.07
    лиÑģ
    -0.07
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.08
    éī´
    0.07
    -focused
    0.07
    alts
    0.07
    éĤ£å°±æĺ¯
    0.07
    主è¦ģå°±æĺ¯
    0.07
     Wilkinson
    0.07
     thoroughly
    0.07
    究竣æĺ¯ä»Ģä¹Ī
    0.07
    question
    0.07
    Activations Density 0.001%

    No Known Activations