© 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. 50663
    Prev
    Next
    INDEX
    Explanations

    website blockers help classifications books

    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
    -0.08
    ingk
    -0.08
     ë°Ķë¡ľ
    -0.07
    ovich
    -0.07
    à¸Ĺà¹Īา
    -0.07
    .enterprise
    -0.07
    à¸ľà¸¹à¹īà¸Īัà¸Ķà¸ģาร
    -0.07
    _INT
    -0.07
    æķ´åº§
    -0.07
    _ENTRY
    -0.07
    POSITIVE LOGITS
    å°ĨæĮīçħ§
    0.08
    à¸ķีà¸Ļ
    0.08
    èģĮä¸ļåѦéĻ¢
    0.08
    à¹ĩà¸ĩ
    0.08
    è¹Ĥ
    0.07
    大æīĵ
    0.07
    é¦ĸæ¬¡åľ¨
    0.07
    èĤ®
    0.07
    大åij¼
    0.07
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.06
    Activations Density 3.527%

    No Known Activations