© 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. 1380
    Prev
    Next
    INDEX
    Explanations

    regex or code patterns

    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
    注
    -0.07
    æľĢåIJİä¸Ģ
    -0.06
     Zan
    -0.06
    ::-
    -0.06
    ^K
    -0.06
    Lastly
    -0.06
    éģĵè¿ľ
    -0.06
     greatly
    -0.06
    (assert
    -0.05
    _LAST
    -0.05
    POSITIVE LOGITS
     بعدÙĩ
    0.09
    éĿĴ天
    0.08
    apar
    0.08
     consecu
    0.08
    ãģĿãģ®ãģ¾ãģ¾
    0.08
    ¤íĥ
    0.08
    ocat
    0.07
    yno
    0.07
    ergeb
    0.07
    ystone
    0.07
    Activations Density 0.010%

    No Known Activations