© 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. 62903
    Prev
    Next
    INDEX
    Explanations

    chronic conditions

    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
    ENTAL
    -0.08
    ished
    -0.08
    antly
    -0.07
    edBy
    -0.07
    æĢ§åĬŁèĥ½
    -0.07
    æĢ§åľ°
    -0.07
    ingat
    -0.07
    emann
    -0.07
    usah
    -0.06
    ÑģÑĮого
    -0.06
    POSITIVE LOGITS
    ear
    0.08
    ub
    0.08
    Ïģθ
    0.08
    il
    0.08
    itch
    0.08
    ora
    0.08
    pu
    0.07
    old
    0.07
    ay
    0.07
    uda
    0.07
    Activations Density 1.053%

    No Known Activations