© 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. 57991
    Prev
    Next
    INDEX
    Explanations

    qualities applied to states

    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
    cede
    -0.08
     itself
    -0.08
    çļĦéĤ£ä¸ª
    -0.08
    ÏĦική
    -0.07
    åĸľéĹ»
    -0.07
    ©
    -0.07
    обÑĢазование
    -0.07
    ofilm
    -0.07
    htable
    -0.07
    коваÑı
    -0.07
    POSITIVE LOGITS
    -looking
    0.10
     themselves
    0.10
     amelyek
    0.10
     kojima
    0.09
     коÑĤоÑĢÑĭе
    0.09
     jotka
    0.09
     których
    0.09
    -sized
    0.08
    ä¸Ģ个个
    0.08
    ippets
    0.08
    Activations Density 1.322%

    No Known Activations