© 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. 57950
    Prev
    Next
    INDEX
    Explanations

    image and code elements

    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
    çİ«çij°
    -0.07
    akk
    -0.07
    %"><
    -0.06
    udu
    -0.06
    peq
    -0.06
    vár
    -0.06
    æķ²
    -0.06
    çļĦ姿åĬ¿
    -0.06
    丰æĶ¶
    -0.06
    並ä¸įæĺ¯
    -0.06
    POSITIVE LOGITS
    æĩ¿
    0.08
    å£ĩ
    0.07
    ª
    0.07
    ä¹ĿæĪIJ
    0.07
    线ä¸Ĭ线ä¸ĭ
    0.07
    dings
    0.07
    egni
    0.06
     ÐķÐĵÐŃ
    0.06
    =sys
    0.06
    inga
    0.06
    Activations Density 0.002%

    No Known Activations