© 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. 33345
    Prev
    Next
    INDEX
    Explanations

    near or close 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
    åŃľåŃľ
    -0.07
    åįĬåľº
    -0.07
    ever
    -0.07
    å¹´å§ĭ
    -0.07
    æħij
    -0.07
    åIJĦåĽ½çļĦ
    -0.07
    ä¸ĩä¸ĩ
    -0.07
    rove
    -0.07
    etos
    -0.07
    æĦ£
    -0.07
    POSITIVE LOGITS
     nhau
    0.11
    à¹Ĩ
    0.08
    ungan
    0.07
     нÑĥлÑı
    0.07
     جدÙĭا
    0.07
    磨
    0.07
    utta
    0.07
    klub
    0.07
     unfavor
    0.06
     Mendes
    0.06
    Activations Density 0.020%

    No Known Activations