© 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. 56109
    Prev
    Next
    INDEX
    Explanations

    finite, exactly, such

    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
    enhagen
    -0.08
    éĤ£èĤ¡
    -0.07
    adian
    -0.07
    opan
    -0.07
    æİ¥åĪ°äºĨ
    -0.07
    /DD
    -0.07
    æĪIJä¸Ģ个
    -0.07
    ä¸ĢèĤ¡
    -0.07
    æİ¥åĪ°
    -0.07
    åıĺæĪIJä¸Ģ个
    -0.07
    POSITIVE LOGITS
    ä»ħæľīçļĦ
    0.09
    æŀļ举
    0.08
    ä»ħæѤ
    0.08
    ä¸Ģä¾ĭ
    0.08
    หล
    0.08
     liá»ĩt
    0.07
     exceptional
    0.07
    æĺ¯åĶ¯ä¸Ģ
    0.07
    exception
    0.07
     cases
    0.07
    Activations Density 0.021%

    No Known Activations