© 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. 45836
    Prev
    Next
    INDEX
    Explanations

    best possible

    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
    avar
    -0.08
    åIJįå±±
    -0.07
    ×ķ׳×Ļ
    -0.07
    ä¸įå®ĮçļĦ
    -0.07
    åİ»ä½ķ
    -0.07
    åĮĸ管çIJĨ
    -0.07
    annya
    -0.07
    TypeEnum
    -0.07
     specifics
    -0.07
    less
    -0.07
    POSITIVE LOGITS
    åĴĮæľĢ
    0.08
     thing
    0.07
    iqué
    0.07
     value
    0.06
    edig
    0.06
    å¸ļ
    0.06
    /generated
    0.06
     helst
    0.06
    ãĥ¼ãĤ«ãĥ¼
    0.06
    ográfico
    0.06
    Activations Density 0.018%

    No Known Activations