© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23389
    Prev
    Next
    INDEX
    Explanations

    indoor championships

    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
    à¸ģาย
    -0.07
    ansch
    -0.07
    à¸ģระà¸Ĺ
    -0.06
     üt
    -0.06
    转载请
    -0.06
    èĦĤèĤªéħ¸
    -0.06
    èĤī身
    -0.06
    Bra
    -0.06
    羯
    -0.06
    rone
    -0.06
    POSITIVE LOGITS
    _callbacks
    0.07
    borgen
    0.07
    obil
    0.07
    iloc
    0.07
    ä¸ĸéĶ¦èµĽ
    0.07
    é¹Ĭ
    0.07
    ä»ĸ乡
    0.07
    -redux
    0.07
    otty
    0.07
    ĥģ
    0.07
    Activations Density 1.726%

    No Known Activations