© 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. 63363
    Prev
    Next
    INDEX
    Explanations

    entry in lists

    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
    ìį¨
    -0.10
    imum
    -0.09
     halnya
    -0.08
    enticator
    -0.08
    æĦıä¹īä¸ĬçļĦ
    -0.08
    ly
    -0.08
    champ
    -0.07
    LY
    -0.07
    Ĺ
    -0.07
    ianne
    -0.07
    POSITIVE LOGITS
    wise
    0.09
    ainte
    0.08
    wizard
    0.08
    udier
    0.08
    Ñİд
    0.08
     sá»ķ
    0.07
    ืà¹īà¸Ń
    0.07
     beiden
    0.07
    ×Ļ
    0.07
    åķĨæĬ¥
    0.07
    Activations Density 0.026%

    No Known Activations