© 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. 1370
    Prev
    Next
    INDEX
    Explanations

    polynomials

    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
     Infinity
    -0.08
     Cet
    -0.08
    ampa
    -0.07
    以ä¸ĭæĿ¡ä»¶
    -0.07
    äh
    -0.07
     ìłľìĻ¸íķľ
    -0.07
    ilah
    -0.07
     Zal
    -0.07
    ahn
    -0.06
    被ç½ļ
    -0.06
    POSITIVE LOGITS
     coefficients
    0.08
    sparse
    0.07
     formula
    0.07
     recursively
    0.07
     matrix
    0.07
    ÑģÑĤавлÑı
    0.07
    matrix
    0.07
    roid
    0.06
    isian
    0.06
     Matrix
    0.06
    Activations Density 0.008%

    No Known Activations