© 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. 48526
    Prev
    Next
    INDEX
    Explanations

    big deal

    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
    -0.08
    -0.07
     duly
    -0.07
    вед
    -0.06
    mant
    -0.06
     niv
    -0.06
    —that
    -0.06
    ®
    -0.06
     fatally
    -0.06
    è®
    -0.06
    POSITIVE LOGITS
    è·¯éĢı
    0.08
    ÏĦαν
    0.08
    ablish
    0.08
    althy
    0.08
    bove
    0.08
    доÑħ
    0.08
    .Summary
    0.08
    .cfg
    0.08
    ÙĪØ©
    0.08
    ×ķ׳×Ļ×Ŀ
    0.08
    Activations Density 0.001%

    No Known Activations