© 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. 21396
    Prev
    Next
    INDEX
    Explanations

    heme proteins

    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
    Ùĭ
    -0.07
    sWith
    -0.07
    æĸĻ
    -0.06
    گاÙĩÛĮ
    -0.06
    迦
    -0.06
    åĴĮ第
    -0.06
    åĴĮéĩįçĤ¹
    -0.06
    ngen
    -0.06
    gehen
    -0.06
    agger
    -0.06
    POSITIVE LOGITS
    -lined
    0.08
    opus
    0.08
    è´¨çļĦ
    0.08
    idine
    0.08
    -like
    0.08
    -rich
    0.08
    aceous
    0.08
    oids
    0.07
    ous
    0.07
    -related
    0.07
    Activations Density 0.180%

    No Known Activations