© 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. 19114
    Prev
    Next
    INDEX
    Explanations

    What if

    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
    unless
    -0.08
     lest
    -0.08
    olv
    -0.07
    lukan
    -0.07
    lest
    -0.07
    thers
    -0.07
    éĻ¤éĿŀ
    -0.07
    ×ij×ķ×ĵ
    -0.07
    ÙĨدÙĩ
    -0.07
    ä¸įå°ijçļĦ
    -0.07
    POSITIVE LOGITS
    æĹ¢èĥ½
    0.09
     instead
    0.09
     Could
    0.09
    ä¸įä»ħèĥ½
    0.08
    Could
    0.08
    åıĪèĥ½
    0.08
    ä¹Łèĥ½
    0.08
     hypoth
    0.08
     systematically
    0.08
    ãģłãģ£ãģŁãĤī
    0.08
    Activations Density 0.361%

    No Known Activations