© 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. 45970
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    ardini
    -0.08
    天马
    -0.07
     Chauss
    -0.07
    åıĬ对
    -0.07
    ÙĨاÙħ
    -0.07
     mene
    -0.07
    æĹ©åıijçİ°
    -0.06
    кок
    -0.06
    Ø®ÛĮ
    -0.06
     Pial
    -0.06
    POSITIVE LOGITS
    .prototype
    0.08
    estan
    0.07
    æģķ
    0.07
    ëħ
    0.06
    writers
    0.06
    ensible
    0.06
    æŃ£ä¸Ń
    0.06
    eric
    0.06
    пÑĢоÑģÑĤÑĢа
    0.06
    GS
    0.06
    Activations Density 0.461%

    No Known Activations