© 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. 28339
    Prev
    Next
    INDEX
    Explanations

    variability, conditions, lambda

    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
    ÙĪغ
    -0.07
     ض
    -0.07
    ochrome
    -0.07
    .bz
    -0.06
    -un
    -0.06
    igel
    -0.06
    éªĭ
    -0.06
    æݺ
    -0.06
     Darling
    -0.06
    μÏīν
    -0.06
    POSITIVE LOGITS
    ucht
    0.08
     ghen
    0.08
    erken
    0.07
    è¡
    0.07
    ignant
    0.07
    åĬŀ好
    0.07
    zni
    0.07
    计ç®Ĺåħ¬å¼ı
    0.07
    opensource
    0.07
    åłĤçļĦ
    0.06
    Activations Density 0.011%

    No Known Activations