© 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. 30012
    Prev
    Next
    INDEX
    Explanations

    hormone replacement or therapy

    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
    å¾ĢæľŁåĽŀ顾
    -0.10
    å¾ĢæľŁç²¾å½©
    -0.09
    ness
    -0.09
    OrCreate
    -0.08
    ëįķ
    -0.07
    égor
    -0.07
     Souls
    -0.07
    /down
    -0.07
    å¸ļ
    -0.07
    ardt
    -0.07
    POSITIVE LOGITS
    ÙĪز
    0.08
    èľľ
    0.08
    villa
    0.07
    ebel
    0.07
    æł·çļĦ
    0.07
    amil
    0.07
    -controlled
    0.07
    uille
    0.07
    oro
    0.07
    beau
    0.07
    Activations Density 0.038%

    No Known Activations