© 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. 14373
    Prev
    Next
    INDEX
    Explanations

    clinical symptoms or manifestations

    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
    esz
    -0.08
    isco
    -0.08
    .onclick
    -0.07
     unfairly
    -0.07
    illion
    -0.07
    å®Īä¿¡
    -0.07
    çĴĭ
    -0.07
    Ế
    -0.07
    缸éĢ¢
    -0.07
    ä¸įåIJĪéĢĤ
    -0.07
    POSITIVE LOGITS
    表çݰ为
    0.16
     symptoms
    0.13
    主è¦ģ表çݰ为
    0.12
    çļĦçĹĩçĬ¶
    0.12
     Symptoms
    0.12
     manifests
    0.12
    çĹĩçĬ¶
    0.12
    manifest
    0.11
     manifest
    0.11
     manifested
    0.11
    Activations Density 0.458%

    No Known Activations