© 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. 24612
    Prev
    Next
    INDEX
    Explanations

    good time

    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
    zcz
    -0.06
    arel
    -0.06
    xel
    -0.06
    åIJįæĢĿ
    -0.06
    è°¨
    -0.06
    jom
    -0.06
    ache
    -0.06
    amon
    -0.06
    ä¹Ŀéĩį
    -0.06
    aur
    -0.06
    POSITIVE LOGITS
    моÑĤ
    0.08
    å±±éķĩ
    0.08
    æĺ¯ä¸įå¤Ł
    0.07
     afterwards
    0.07
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    0.07
    ayo
    0.07
     Haley
    0.07
    gång
    0.07
     afterward
    0.07
     sót
    0.07
    Activations Density 0.049%

    No Known Activations