© 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. 33190
    Prev
    Next
    INDEX
    Explanations

    inflammation or disease

    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
    wis
    -0.08
    itions
    -0.08
    sworth
    -0.08
    ings
    -0.08
    stants
    -0.08
    OrDefault
    -0.08
    ugin
    -0.08
    ments
    -0.07
    nings
    -0.07
    помним
    -0.07
    POSITIVE LOGITS
    çŃīçĸ¾çĹħ
    0.09
     caused
    0.08
    åıijçĶŁåIJİ
    0.08
     ÙĨاش
    0.07
     mell
    0.07
    é¢ijåıij
    0.07
    -associated
    0.07
     occurring
    0.07
     occurs
    0.07
    /DD
    0.07
    Activations Density 0.509%

    No Known Activations