© 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. 12592
    Prev
    Next
    INDEX
    Explanations

    in the context of

    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
    å¤§å®¶åľ¨
    -0.08
    ़
    -0.08
    ä»·æł¼åľ¨
    -0.08
    产åĵģåľ¨
    -0.08
    ť
    -0.08
    åıĮæĸ¹åľ¨
    -0.08
    sters
    -0.08
    éļIJèĹıåľ¨
    -0.07
    ting
    -0.07
    åľ¨å¸Ĥåľºä¸Ĭ
    -0.07
    POSITIVE LOGITS
     midst
    0.17
     meantime
    0.12
     vicinity
    0.12
     accordance
    0.12
     guise
    0.11
    sofar
    0.11
    /out
    0.10
    quis
    0.09
    appropri
    0.09
     lieu
    0.09
    Activations Density 0.749%

    No Known Activations