© 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. 42890
    Prev
    Next
    INDEX
    Explanations

    health outcomes risk factors

    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
    nga
    -0.08
    ãģİ
    -0.08
    åİŁåĪĽæĸĩç«ł
    -0.07
    管åĴĮ
    -0.06
    祥
    -0.06
    amore
    -0.06
    .inter
    -0.06
    ordo
    -0.06
    åĢºåĬ¡åĪ©æģ¯
    -0.06
    éĽ
    -0.06
    POSITIVE LOGITS
     outcomes
    0.09
     outcome
    0.09
     behaviour
    0.08
    è·ijåĩº
    0.08
     Outcome
    0.07
     offens
    0.07
    æķıæĦŁçļĦ
    0.07
    atil
    0.07
    æ²īæµ®
    0.07
     multif
    0.07
    Activations Density 0.212%

    No Known Activations