© 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. 29433
    Prev
    Next
    INDEX
    Explanations

    descriptive nouns and terms

    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
    à¹ĥหมà¹Īà¸Ĥà¸Ńà¸ĩ
    -0.10
    สำà¸Ħัà¸įà¸Ĥà¸Ńà¸ĩ
    -0.10
    éĹ®é¢ĺæĿ¥äºĨ
    -0.09
    æľīæĹł
    -0.08
    åħ·ä½ĵéĹ®é¢ĺ
    -0.08
     име
    -0.08
    ipot
    -0.08
     oneself
    -0.08
    èµ·è§ģ
    -0.08
    лÑĥÑĥ
    -0.08
    POSITIVE LOGITS
    åı¯è¨Ģ
    0.11
    åı¯å¾ª
    0.09
     tersendiri
    0.09
    å±ŀäºİèĩªå·±çļĦ
    0.09
    èĩªå·±çļĦ
    0.09
    æĺ¯åħ¶
    0.09
    åı¯ä¾Ŀ
    0.08
     ÑģвоиÑħ
    0.08
    åľ¨èº«
    0.08
    à¸Ńยูà¹Īà¹ģลà¹īว
    0.08
    Activations Density 0.713%

    No Known Activations