© 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. 8110
    Prev
    Next
    INDEX
    Explanations

    add 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
    acles
    -0.08
    å·¨åıĺ
    -0.07
    人ä¹ĭ
    -0.07
     prochaines
    -0.06
    anders
    -0.06
     dodatk
    -0.06
     Additional
    -0.06
    åľ¨å®¶éĩĮ
    -0.06
     عÙĦÙĬÙĥ
    -0.06
    å·¥ä½ľä¸ĬçļĦ
    -0.06
    POSITIVE LOGITS
     behalf
    0.10
    å·²æľīçļĦ
    0.10
    _existing
    0.09
    åİŁæľīçļĦ
    0.09
    æĹ¢åŃĺ
    0.09
     existing
    0.09
    /from
    0.09
     each
    0.09
    å·²ç»ıå¾Ī
    0.09
    çİ°æľīçļĦ
    0.09
    Activations Density 0.313%

    No Known Activations