© 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. 19936
    Prev
    Next
    INDEX
    Explanations

    often

    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
     presumably
    -0.08
     surely
    -0.07
    æĺ¾çĦ¶
    -0.07
    ä½ķ
    -0.07
     denn
    -0.06
    atorio
    -0.06
    opus
    -0.06
    åĴĮæľªæĿ¥
    -0.06
     Surely
    -0.06
    andum
    -0.06
    POSITIVE LOGITS
    å¾Ģå¾Ģæĺ¯
    0.14
    å¾Ģå¾Ģ
    0.13
     sometimes
    0.13
     often
    0.13
     Sometimes
    0.12
     бÑĭваеÑĤ
    0.12
    æľīæŶåĢĻ
    0.11
    æľīæŶä¼ļ
    0.11
     Often
    0.11
     parfois
    0.11
    Activations Density 0.036%

    No Known Activations