© 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. 15239
    Prev
    Next
    INDEX
    Explanations

    orthonormal vectors and product spaces

    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
    ستاÙĨ
    -0.09
    änger
    -0.09
    _iters
    -0.08
    sche
    -0.08
    лÑĮÑİ
    -0.07
    jenigen
    -0.07
    isters
    -0.07
    eways
    -0.07
    neys
    -0.07
    à°£
    -0.07
    POSITIVE LOGITS
    ormal
    0.12
     Kens
    0.08
    autical
    0.07
    inia
    0.07
    ive
    0.07
    inals
    0.07
    bie
    0.07
    Ùħز
    0.07
    /OR
    0.07
     اÛĮÙĨÚ©Ùĩ
    0.07
    Activations Density 0.001%

    No Known Activations