© 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. 29263
    Prev
    Next
    INDEX
    Explanations

    drainage and flow

    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
    áĥ£áĥłáĥĺ
    -0.11
    gether
    -0.10
    ï¸ı
    -0.10
    ebra
    -0.09
    ï¸İ
    -0.09
    oulouse
    -0.09
    enskap
    -0.09
    новÑĮ
    -0.09
    룬ìĬ¤
    -0.08
     kelamin
    -0.08
    POSITIVE LOGITS
    æĭ¢
    0.08
    æĪIJç«ł
    0.07
    าà¸Ļ
    0.06
    ussin
    0.06
    æķ´é½IJçļĦ
    0.06
    manent
    0.06
    haps
    0.06
     conséquent
    0.06
    ä¼¼éĶ¦
    0.06
    å½ĵãģ¦
    0.06
    Activations Density 0.004%

    No Known Activations