© 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. 27818
    Prev
    Next
    INDEX
    Explanations

    beginning of uncertainty

    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
    éĤ£åı¯æĺ¯
    -0.08
    è¿Ļåı¯æĺ¯
    -0.08
     presumably
    -0.08
     reportedly
    -0.08
    æĪijåı¯æĺ¯
    -0.08
    åı¯ä¸įæĺ¯
    -0.08
     assolutamente
    -0.07
    ä¸ĢèĪ¬éĥ½
    -0.07
    ä¸ĢåĽŀäºĭ
    -0.07
    çĽ¸ä¼ł
    -0.07
    POSITIVE LOGITS
    Maybe
    0.07
     Maybe
    0.07
    ú
    0.07
    èij±èij±
    0.07
     maybe
    0.07
    maybe
    0.07
    cratch
    0.06
    Ø·Ùħ
    0.06
    åĩºä¸Ģéģĵ
    0.06
    ÑĤеÑģÑĮ
    0.06
    Activations Density 0.068%

    No Known Activations