© 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. 28537
    Prev
    Next
    INDEX
    Explanations

    covariant, covariates, derivative, density, multivariate

    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
    ×ķ×ŀ
    -0.08
    psilon
    -0.07
    cock
    -0.06
    umph
    -0.06
    evity
    -0.06
     volna
    -0.06
     vastly
    -0.06
    جات
    -0.06
    awai
    -0.06
    vice
    -0.06
    POSITIVE LOGITS
    iously
    0.11
    ly
    0.09
    /general
    0.09
    ainty
    0.09
    adini
    0.09
    ariant
    0.08
    atively
    0.08
    ely
    0.08
    æĦıä¹īä¸ĬçļĦ
    0.08
    åħ¶èģĮ
    0.08
    Activations Density 0.006%

    No Known Activations