© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14883
    Prev
    Next
    INDEX
    Explanations

    most money, grew, happiest, land, commented, reviews, fastest

    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
    ä¸įåĨįæĺ¯
    -0.09
    ä¸įåĨį
    -0.08
    ä¹Łä¸įåĨį
    -0.08
    æľīäºĨå¾Ī大çļĦ
    -0.07
    çļĦèī¯å¥½
    -0.07
    ä¸įåĨįæľī
    -0.07
    å¾Īæĺ¯
    -0.07
    redi
    -0.07
    å¾Īç®Ģåįķ
    -0.07
     betul
    -0.07
    POSITIVE LOGITS
    æ¯Ķåħ¶ä»ĸ
    0.10
    åĴĮæľĢ
    0.09
    çĽ¸å¯¹èĢĮè¨Ģ
    0.08
    è§Ħ模æľĢ大
    0.08
     наиб
    0.08
    ä¹Łæĺ¯æľĢ
    0.08
     fastest
    0.08
    æľĢãĤĤ
    0.08
    æľĢåħĪ
    0.08
     наим
    0.08
    Activations Density 0.126%

    No Known Activations