© 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. 39663
    Prev
    Next
    INDEX
    Explanations

    from the song

    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
    åĽł
    -0.07
    æĭĶ
    -0.06
    æĻļ
    -0.06
     AUTHOR
    -0.06
    kos
    -0.06
    finally
    -0.06
    atici
    -0.06
    åĽłåħ¬
    -0.06
    è¯Ŀ说
    -0.06
    èŁ¹
    -0.06
    POSITIVE LOGITS
    Ñĩан
    0.08
     Å¡i
    0.07
    ÑĢÑģ
    0.07
    è¾¾æĸ¯
    0.07
    Ø«
    0.07
    ×Ļ׾
    0.07
     sợ
    0.07
    chetti
    0.07
    建æĪ¿
    0.07
    ruz
    0.07
    Activations Density 0.001%

    No Known Activations