© 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. 47885
    Prev
    Next
    INDEX
    Explanations

    health behaviors and promotion

    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
    ืà¸Ńà¸Ļ
    -0.07
    sak
    -0.07
    agod
    -0.07
    Äįer
    -0.07
    ERP
    -0.07
    ÙĦÛĮÙĦ
    -0.07
    ÙĬرة
    -0.07
    å¤ľæ·±
    -0.06
     tern
    -0.06
    akra
    -0.06
    POSITIVE LOGITS
     health
    0.15
    health
    0.13
    Health
    0.13
    åģ¥åº·
    0.13
     Health
    0.13
     lifestyle
    0.13
    -health
    0.12
     wellness
    0.12
    çļĦåģ¥åº·
    0.12
    åģ¥åº·çļĦ
    0.12
    Activations Density 0.428%

    No Known Activations