© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30106
    Prev
    Next
    INDEX
    Explanations

    linking data and clinical

    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
    i
    -0.09
    稽
    -0.07
    ous
    -0.06
    á»ı
    -0.06
    yll
    -0.06
    peed
    -0.06
    ı
    -0.06
    पà¥Ģ
    -0.06
    oid
    -0.06
    ï¿£
    -0.06
    POSITIVE LOGITS
    DMIN
    0.08
    жев
    0.08
    ROTO
    0.08
    ngth
    0.08
    tran
    0.08
    ÛĮ
    0.07
    åIJijèį£
    0.07
    arli
    0.07
    िà¤ı
    0.07
    ncia
    0.07
    Activations Density 0.002%

    No Known Activations