© 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. 46849
    Prev
    Next
    INDEX
    Explanations

    if it exists

    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
     probably
    -0.11
    ä¹ĭæīĢ以
    -0.11
     almost
    -0.09
     therefore
    -0.09
    äºĨåIJĹ
    -0.09
    probably
    -0.08
     arguably
    -0.08
    æĤ¨åı¯èĥ½
    -0.08
     поÑįÑĤомÑĥ
    -0.08
     wiÄĻc
    -0.08
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.13
    å¤įåĪ¶æĪĸ
    0.12
    çļĦ話
    0.10
    éĤ£ä¸įæĺ¯
    0.10
    æĬķèµĦæĪĸ
    0.10
    羣çļĦæľī
    0.10
    ä¸įè¿ĩäºĨ
    0.09
    à¸ģà¹ĩà¸ķาม
    0.09
    éĤ£ä»ĸ
    0.09
    éĤ£å°±æĺ¯
    0.09
    Activations Density 0.111%

    No Known Activations