© 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. 7464
    Prev
    Next
    INDEX
    Explanations

    behind a shopping center

    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
    scri
    -0.07
    ×ĺ×Ļפ
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    èѬå¦Ĥ
    -0.07
    ¾¸
    -0.07
    avantage
    -0.07
    ommage
    -0.07
    ugins
    -0.07
    strap
    -0.07
    .toJSON
    -0.07
    POSITIVE LOGITS
    æĸ¹åľĨ
    0.08
    第äºĮ天
    0.08
    为æѤ
    0.07
    ä½łè§īå¾Ĺ
    0.06
    äºĭåIJİ
    0.06
    éĹ®è¿ĩ
    0.06
    è¿Ļ个æ¶Īæģ¯
    0.06
    天ä¸ĭ
    0.06
    ä¹ħèĢĮä¹ħä¹ĭ
    0.06
    åıĪå¿«
    0.06
    Activations Density 0.163%

    No Known Activations