© 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. 16328
    Prev
    Next
    INDEX
    Explanations

    orthonormal basis

    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
    ecker
    -0.08
    krit
    -0.08
    inato
    -0.08
    druk
    -0.08
    enhagen
    -0.08
    íĻį
    -0.08
    obar
    -0.08
    ngo
    -0.08
    IDL
    -0.08
    .jquery
    -0.08
    POSITIVE LOGITS
    åĪ¶
    0.07
     orth
    0.07
    ç«Ļ
    0.06
     danced
    0.06
     Orth
    0.06
    èĬ·
    0.06
    igan
    0.06
    è¹´
    0.06
     Gaussian
    0.06
    太æŀģæĭ³
    0.06
    Activations Density 0.008%

    No Known Activations