© 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. 13472
    Prev
    Next
    INDEX
    Explanations

    cooktop, biodiesel, drug trafficking, blurred vision

    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
    endt
    -0.07
    å¥Īä½ķ
    -0.06
    ent
    -0.06
    okens
    -0.06
    éģ
    -0.06
    ably
    -0.06
    ILE
    -0.06
     place
    -0.06
    undos
    -0.06
     ТеÑħнологи
    -0.05
    POSITIVE LOGITS
    alz
    0.08
    uyên
    0.08
    alb
    0.08
    æł·æł·
    0.08
    .invoke
    0.08
    .factory
    0.08
    epas
    0.07
    ниÑĩеÑģÑĤво
    0.07
    .argument
    0.07
    BitFields
    0.07
    Activations Density 0.023%

    No Known Activations