© 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. 18590
    Prev
    Next
    INDEX
    Explanations

    describing states or conditions

    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
    ä¸ĭåIJĮ
    -0.09
     Lainnya
    -0.09
    saan
    -0.08
    åħ°çī¹
    -0.08
    ainya
    -0.08
     Ãľl
    -0.08
    лаго
    -0.08
    áĭŃ
    -0.08
    çĻ»ä¸ĬäºĨ
    -0.08
     Yüks
    -0.08
    POSITIVE LOGITS
    ÂŃ
    0.07
    ãĢģãĢģ
    0.07
     [âĢ¦]
    0.06
    .setdefault
    0.06
    ､
    0.06
    ÙĮ
    0.06
    ��
    0.06
    æĪĸèĢħ
    0.06
     _______,
    0.06
    å±±æĻ¯åĮº
    0.06
    Activations Density 5.227%

    No Known Activations