© 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. 24857
    Prev
    Next
    INDEX
    Explanations

    therapy and therapeutic 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
    itude
    -0.10
    ness
    -0.09
    ãģ¾ãģ¾
    -0.08
    ervo
    -0.08
    eens
    -0.07
    eer
    -0.07
    zinho
    -0.07
    ermann
    -0.07
    ured
    -0.07
    heritance
    -0.07
    POSITIVE LOGITS
    ilit
    0.08
    ilitating
    0.08
    iously
    0.08
    ystack
    0.08
    fici
    0.08
    eka
    0.08
    anjutkan
    0.08
    manent
    0.08
    ilitation
    0.07
    neh
    0.07
    Activations Density 0.063%

    No Known Activations