© 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. 41585
    Prev
    Next
    INDEX
    Explanations

    from to

    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
    _updated
    -0.07
    oger
    -0.07
    osex
    -0.06
    设å¤ĩåıĬ
    -0.06
     contraire
    -0.06
    .
    -0.06
    unek
    -0.06
    èĬ±å²Ĺ
    -0.06
    _wrapper
    -0.06
    æľīæķĪæľŁèĩª
    -0.05
    POSITIVE LOGITS
    转åıĺ为
    0.10
    åĪ°çı¾åľ¨
    0.09
    åıĺ为
    0.09
    èĢĮæĺ¯
    0.09
    å®ŀéĻħåĩºåıij
    0.09
    çİ°åľ¨å¼Ģå§ĭ
    0.08
    åĪ°å¦Ĥä»Ĭ
    0.08
    åĨįåĪ°
    0.08
    ä¹ĭæĹ¥èµ·
    0.08
    èĢĮçİ°åľ¨
    0.08
    Activations Density 0.099%

    No Known Activations