© 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. 21925
    Prev
    Next
    INDEX
    Explanations

    expand or grow

    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
    -0.11
    дика
    -0.09
    mite
    -0.09
    оп
    -0.08
    ihan
    -0.08
    hood
    -0.08
    -même
    -0.08
     Fanpage
    -0.08
    ÙĦد
    -0.08
    jada
    -0.07
    POSITIVE LOGITS
    ibility
    0.08
    ively
    0.08
    es
    0.08
    ansion
    0.08
    ible
    0.07
    odied
    0.07
    ãģªãģĬ
    0.07
    ément
    0.07
    壮大çļĦ
    0.07
    issage
    0.07
    Activations Density 0.030%

    No Known Activations