© 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. 16138
    Prev
    Next
    INDEX
    Explanations

    substances or physical forms

    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
    æĢ§æĪĸ
    -0.09
    æĬķèµĦæĪĸ
    -0.09
    æĪĸæĺ¯
    -0.08
    æĪĸ被
    -0.07
    INY
    -0.07
    éĶĻ误æĪĸ
    -0.07
    ách
    -0.07
    æĬijæĪĸ
    -0.07
    æĪĸåħ¶
    -0.07
     either
    -0.07
    POSITIVE LOGITS
    ä¸ĩåĽ½
    0.08
    说起
    0.08
    çĽ¸å¯¹çļĦ
    0.07
    æĸ°éĻĪ代谢
    0.07
    åı¯ä»¥è¯´æĺ¯
    0.07
    agra
    0.07
    称
    0.07
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.07
    iori
    0.07
    meras
    0.07
    Activations Density 0.206%

    No Known Activations