© 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. 2641
    Prev
    Next
    INDEX
    Explanations

    antibiotics and medical treatments

    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
    oura
    -0.07
    á»ijn
    -0.07
    ublisher
    -0.06
    ohner
    -0.06
    atori
    -0.06
    ras
    -0.06
    ilst
    -0.06
     mpl
    -0.06
    åĪĬ
    -0.06
    ä¹ĭäºĮ
    -0.06
    POSITIVE LOGITS
    azine
    0.08
    æĪĸåħ¶
    0.08
    ä½ķåĨµ
    0.08
    -inspired
    0.08
    ’s
    0.07
    à¸Ľà¸ģรà¸ĵà¹Į
    0.07
    à¸Ħà¹Į
    0.07
    åıĬåħ¶
    0.07
    ارÙĤ
    0.07
    lean
    0.07
    Activations Density 0.061%

    No Known Activations