© 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. 4396
    Prev
    Next
    INDEX
    Explanations

    content describing something

    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
    rå
    -0.07
    èĨĺ
    -0.07
    lösung
    -0.07
    å¾ģ稿
    -0.07
    onton
    -0.07
     sympath
    -0.07
     amb
    -0.07
     ambi
    -0.07
    æĹ¥åIJij
    -0.06
    ãģĤ
    -0.06
    POSITIVE LOGITS
    iebe
    0.08
    arit
    0.07
    ÙĪعة
    0.07
    _SCOPE
    0.07
    à¤ľà¤¨
    0.07
    ohn
    0.07
    urtle
    0.07
    ÏĦÎŃÏģ
    0.07
     Ñįле
    0.06
    æīĵäºĨ
    0.06
    Activations Density 0.001%

    No Known Activations