© 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. 21243
    Prev
    Next
    INDEX
    Explanations

    related to eyes

    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
    ively
    -0.09
    ering
    -0.09
    idor
    -0.08
     Setia
    -0.08
    ional
    -0.08
    ities
    -0.08
    ãĤĵãģ³
    -0.08
    à¹Ĥว
    -0.07
    luan
    -0.07
    à¸ĩ
    -0.07
    POSITIVE LOGITS
    -catching
    0.08
    wards
    0.08
    uate
    0.07
    wright
    0.07
    ures
    0.07
    fulness
    0.07
    uche
    0.07
    socket
    0.07
    lixir
    0.07
    lessly
    0.07
    Activations Density 0.027%

    No Known Activations