© 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. 1139
    Prev
    Next
    INDEX
    Explanations

    defining domains

    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
    æĥħåĨµè¿Ľè¡ĮäºĨ
    -0.10
    bable
    -0.10
    æĥħåĨµåIJİ
    -0.09
    é£ŀåİ»
    -0.09
    æľĿ天
    -0.09
    achten
    -0.09
    çĴĢ
    -0.09
    以ä¸ĭæĿ¡ä»¶
    -0.08
    reira
    -0.08
    åıĮä¼ij
    -0.08
    POSITIVE LOGITS
     terminology
    0.09
    æľ¯è¯Ń
    0.09
     often
    0.07
    éĢļ常
    0.07
     notation
    0.07
     terms
    0.07
    å¾Ģå¾Ģ
    0.07
    å¾Īå¤ļæŶåĢĻ
    0.07
    arm
    0.07
     typically
    0.07
    Activations Density 0.097%

    No Known Activations