© 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. 12938
    Prev
    Next
    INDEX
    Explanations

    image blurring and resolution

    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
    rane
    -0.08
    éĵŃ
    -0.08
    osu
    -0.08
    æł¼å°Ķ
    -0.08
    λογ
    -0.07
     Nego
    -0.07
    egno
    -0.07
    girl
    -0.07
    odar
    -0.07
    ạng
    -0.07
    POSITIVE LOGITS
     blur
    0.11
    blur
    0.10
    æķ£
    0.10
     jitter
    0.09
    æĬĸåĬ¨
    0.09
     smear
    0.09
    æķ£äºĨ
    0.09
    /stretch
    0.08
     dispersion
    0.08
    宽度
    0.08
    Activations Density 0.030%

    No Known Activations