© 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. 19710
    Prev
    Next
    INDEX
    Explanations

    nested structures or original code

    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
     Frieden
    -0.07
    appen
    -0.07
    áĥĽáĥIJ
    -0.06
    ัà¸į
    -0.06
    举éŨ
    -0.06
    bench
    -0.06
    è¿ĶåĽŀ顶éĥ¨
    -0.06
    /rfc
    -0.06
    éªı
    -0.06
    Ñĥда
    -0.06
    POSITIVE LOGITS
    æĭ¥
    0.08
    orig
    0.08
    ç¹ģ
    0.08
    _nested
    0.08
    _orig
    0.08
    ÙĦاÙĨ
    0.07
    å¤įæĿĤçļĦ
    0.07
    ocator
    0.07
    æĵģ
    0.07
    ç¹ģæĿĤ
    0.07
    Activations Density 0.056%

    No Known Activations