© 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. 14815
    Prev
    Next
    INDEX
    Explanations

    metabolic and abolic processes

    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
    ness
    -0.08
     sanitaire
    -0.08
    UNUSED
    -0.08
    ÑģÑĤÑĮ
    -0.07
    ified
    -0.07
    ุà¹Īà¸Ļ
    -0.07
    ames
    -0.07
    ationen
    -0.07
    mozilla
    -0.07
    داÙħ
    -0.07
    POSITIVE LOGITS
    credi
    0.08
    licity
    0.08
    ically
    0.08
    ogy
    0.08
    CGRect
    0.07
    ting
    0.07
    à¸Ļà¹Į
    0.07
    óg
    0.07
    ieber
    0.07
    à¸ľà¸ªà¸²à¸Ļ
    0.07
    Activations Density 0.026%

    No Known Activations