© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14977
    Prev
    Next
    INDEX
    Explanations

    is accredited / are required

    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
    !
    -0.07
    æĺ¯æĮĩåľ¨
    -0.06
    åħ·æľī以ä¸ĭ
    -0.06
     -
    -0.06
    rie
    -0.06
    جÙĩ
    -0.06
    uest
    -0.05
    ze
    -0.05
    roup
    -0.05
    arian
    -0.05
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.10
    æľĢåIJİæĺ¯
    0.09
    Ïģγο
    0.08
    èŀŁ
    0.08
    sgi
    0.08
    _SIG
    0.08
    mee
    0.08
    èĩªå¸¦çļĦ
    0.08
    é¹ĥ
    0.08
    ::$
    0.08
    Activations Density 0.060%

    No Known Activations