© 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. 10762
    Prev
    Next
    INDEX
    Explanations

    immunosuppression and vulnerability

    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
    ÙĪبر
    -0.08
    .requires
    -0.07
    Äį
    -0.07
    gsub
    -0.07
    _gas
    -0.07
     rozwiÄħ
    -0.07
    abel
    -0.07
    å¾ĪèĪĴæľį
    -0.07
     Sanity
    -0.07
    uruh
    -0.07
    POSITIVE LOGITS
     vulnerability
    0.21
     vulnerable
    0.18
     Vulner
    0.18
    èĦĨå¼±
    0.18
     vulnerabilities
    0.17
     susceptibility
    0.16
     vulner
    0.15
     susceptible
    0.14
    æĺĵ
    0.13
    æĽ´å®¹æĺĵ
    0.13
    Activations Density 0.307%

    No Known Activations