© 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. 44810
    Prev
    Next
    INDEX
    Explanations

    on: or whilst

    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
    akis
    -0.08
    ç¢į
    -0.07
     specific
    -0.07
     Pré
    -0.07
    urch
    -0.07
     Ingl
    -0.07
     Wenger
    -0.07
    ç¡®åĪĩ
    -0.07
    specific
    -0.06
    ediator
    -0.06
    POSITIVE LOGITS
    继ç»Ń
    0.09
     continue
    0.08
    æĶ¶æķĽ
    0.07
    å¥ī
    0.07
     continuing
    0.07
    continue
    0.07
    ç¹¼çºĮ
    0.07
    ehl
    0.07
    以ä¸Ĭæĺ¯
    0.07
     continues
    0.07
    Activations Density 0.002%

    No Known Activations