© 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. 64409
    Prev
    Next
    INDEX
    Explanations

    carbonyl group or compounds

    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
    ively
    -0.08
    اÙĭ
    -0.07
    gs
    -0.07
    <|box_end|>
    -0.07
    ering
    -0.07
    ovsky
    -0.07
    comings
    -0.07
    ileo
    -0.07
    fully
    -0.07
    ely
    -0.07
    POSITIVE LOGITS
    s
    0.08
    icin
    0.08
    sWith
    0.08
    ì§Ŀ
    0.08
    عاÙĦ
    0.07
    atted
    0.07
    scape
    0.07
    åľ¨ä¸Ńåľĭ
    0.07
    ounge
    0.07
    ات
    0.07
    Activations Density 0.003%

    No Known Activations