© 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. 24963
    Prev
    Next
    INDEX
    Explanations

    cases of COVID-19

    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
    anio
    -0.09
    ç«ĭæ¡Īä¿¡æģ¯
    -0.09
    è¿Ŀæ³ķåĴĮä¸įèī¯
    -0.08
    AccessException
    -0.08
     sottos
    -0.08
    Slave
    -0.07
    åĩºè´¨
    -0.07
    é¢ĦéĢī
    -0.07
    ÙĪرش
    -0.07
    å©ļåIJİ
    -0.07
    POSITIVE LOGITS
    åįĥ人
    0.08
    人群
    0.08
    åħ¬åħ±åľºæīĢ
    0.08
     pneumonia
    0.08
     Variant
    0.08
     epidemi
    0.08
    Variant
    0.08
     variante
    0.07
    ä½ĵ温
    0.07
    çĹħæ¯Ĵ
    0.07
    Activations Density 0.157%

    No Known Activations