© 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. 8424
    Prev
    Next
    INDEX
    Explanations

    sounds quirky or unusual

    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
    या
    -0.08
    åIJ¦åĪĻä¼ļ
    -0.08
    ichter
    -0.07
    rect
    -0.07
    ibbon
    -0.07
     EITHER
    -0.07
    çĻ»å½ķåIJİ
    -0.07
    á»Ĺi
    -0.07
    eyer
    -0.07
    KHR
    -0.06
    POSITIVE LOGITS
     admittedly
    0.09
    æĺİçŁ¥
    0.09
    ä½Ĩè¿Ļ
    0.08
    çķ¥æĺ¾
    0.08
    æľīçĤ¹
    0.08
     slightly
    0.08
     ÐĹаÑĤо
    0.08
    ä½Ĩåı¯ä»¥
    0.08
    æľīé£İéĻ©
    0.07
    äºĨäºĽ
    0.07
    Activations Density 0.267%

    No Known Activations