© 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. 28835
    Prev
    Next
    INDEX
    Explanations

    explaining or using something

    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
    èĭ¥
    -0.08
     ’
    -0.07
    èĻ½
    -0.07
    ronym
    -0.07
    ’
    -0.07
    èĻ
    -0.07
     amid
    -0.06
    åį³ä¾¿
    -0.06
    åĵªæĢķ
    -0.06
    POSITIVE LOGITS
    ä»Ĭ天å°ıç¼ĸå°±
    0.08
    uko
    0.08
    åľ¨è¿Ļ个è¿ĩç¨ĭä¸Ń
    0.07
    olit
    0.07
    åľ¨å¹¿å·ŀ
    0.07
     webshop
    0.07
     **—
    0.07
    æ£Ł
    0.07
    éĹ®åĪ°
    0.07
     **âĢ¢
    0.07
    Activations Density 0.012%

    No Known Activations