© 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. 27292
    Prev
    Next
    INDEX
    Explanations

    event management

    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
    åį´åıijçİ°
    -0.07
    漪
    -0.07
    嫦
    -0.07
    agnes
    -0.07
    odes
    -0.07
    æIJ
    -0.07
    urunk
    -0.07
    ãģĿãĤĮãģĮ
    -0.06
    çĿĢçī©
    -0.06
    sworth
    -0.06
    POSITIVE LOGITS
    ä¼ĹæīĢåij¨çŁ¥
    0.09
    顾åIJįæĢĿä¹ī
    0.09
    èĻ½çĦ¶åľ¨
    0.09
    ä¿Ĺè¯Ŀ说
    0.08
    èĻ½è¯´
    0.08
    ä¸ĢèĪ¬æĿ¥è¯´
    0.08
    perk
    0.08
     Although
    0.08
    èĻ½çĦ¶è¯´
    0.08
    çĶ±äºİ
    0.08
    Activations Density 0.279%

    No Known Activations