© 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. 8523
    Prev
    Next
    INDEX
    Explanations

    specifies

    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
    ajer
    -0.10
    请çĤ¹åĩ»
    -0.09
    秣åĶ®
    -0.09
     @$
    -0.08
     =>$
    -0.08
    .ListView
    -0.08
    .hasClass
    -0.08
    ippi
    -0.08
    ढ
    -0.08
    _pickle
    -0.08
    POSITIVE LOGITS
     specifies
    0.09
    Specifies
    0.09
    Specify
    0.08
    æĮĩå®ļ
    0.08
    æĺ¯çĶ¨æĿ¥
    0.08
    optional
    0.08
    Âł
    0.08
    è¿Ļ个æķ°åŃĹ
    0.08
     optional
    0.08
     Specifies
    0.08
    Activations Density 0.114%

    No Known Activations