© 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. 38170
    Prev
    Next
    INDEX
    Explanations

    expected results or findings

    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
     formulas
    -0.07
     formula
    -0.07
    广ä¹ī
    -0.07
    åħ¨éĥ¨éĥ½æĺ¯
    -0.07
    çĭŃ
    -0.07
     implicitly
    -0.07
    mailto
    -0.07
    HeaderValue
    -0.06
    iling
    -0.06
    计ç®Ĺåħ¬å¼ı
    -0.06
    POSITIVE LOGITS
     expected
    0.13
    æĻ¯è±¡
    0.12
    é¢ĦæľŁ
    0.12
    expected
    0.12
    é¢ĦæľŁçļĦ
    0.11
    é¢ĦæĸĻ
    0.11
    æııè¿°
    0.11
    éłIJæľŁ
    0.10
     Expected
    0.10
     ожида
    0.10
    Activations Density 0.119%

    No Known Activations