© 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. 42850
    Prev
    Next
    INDEX
    Explanations

    medical reference abstracts

    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
    éĿŀåħ¸
    -0.10
    @yahoo
    -0.09
    åįģä¸ĢäºĶ
    -0.08
     мили
    -0.08
    好象
    -0.08
     yahoo
    -0.07
     videot
    -0.07
     idéia
    -0.07
    .googlecode
    -0.07
    èĥ¡éĶ¦æ¶Ľ
    -0.07
    POSITIVE LOGITS
     constexpr
    0.10
    乡æĿijæĮ¯åħ´
    0.10
    (nameof
    0.10
    https
    0.10
    COVID
    0.09
     https
    0.09
    ä¸įå¿ĺåĪĿå¿ĥ
    0.09
     COVID
    0.09
     emojis
    0.09
    emoji
    0.09
    Activations Density 0.186%

    No Known Activations