© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59838
    Prev
    Next
    INDEX
    Explanations

    either costs units

    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
    Negative Logits
    olk
    -0.08
    ä¿ĿçķĻ
    -0.08
    elson
    -0.08
    egd
    -0.08
     retaining
    -0.08
    æıIJä¾ĽåIJĦç§į
    -0.08
    æ¯ıä¸Ģç§į
    -0.07
    æľīä¸į
    -0.07
    è¦ģæ±Ĥèĩªå·±
    -0.07
    ä¿ĿçķĻäºĨ
    -0.07
    POSITIVE LOGITS
    æ³¢åıĬ
    0.09
    åĮħæĭ¬
    0.08
    èĮĥåĽ´å¹¿
    0.07
    沿éĢĶ
    0.07
    èĮĥåĽ´
    0.07
    åĮħæĭ¬äºĨ
    0.07
     unsus
    0.07
    WithTag
    0.07
    涵çĽĸ
    0.07
     future
    0.07
    Activations Density 0.094%

    No Known Activations