© 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. 39655
    Prev
    Next
    INDEX
    Explanations

    medical conditions and adverse events

    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
    OrCreate
    -0.08
    pit
    -0.08
     available
    -0.07
     Available
    -0.07
    Available
    -0.07
    oreach
    -0.07
    cente
    -0.07
    .failure
    -0.07
    åīįå¤ķ
    -0.07
     slap
    -0.06
    POSITIVE LOGITS
    æļĤæŶ
    0.09
    ibold
    0.09
     revert
    0.09
    åĽŀåİ»äºĨ
    0.09
     temporary
    0.09
    temporary
    0.09
    :return
    0.09
    éļıçĿĢæŶéĹ´çļĦ
    0.09
     Temporary
    0.09
    éĢĨ
    0.08
    Activations Density 0.267%

    No Known Activations