© 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. 61116
    Prev
    Next
    INDEX
    Explanations

    sparse matrix algorithms

    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
    å·¡è§Ĩåijĺ
    -0.09
     Aufenthalts
    -0.08
    éĢłæĪIJ伤害
    -0.08
    uppe
    -0.08
    纶
    -0.08
    æij©
    -0.08
    natal
    -0.07
    éĢłçī©
    -0.07
    Mes
    -0.07
    åĬŁåĪ©
    -0.07
    POSITIVE LOGITS
    ç¨Ģçĸı
    0.08
     Algorithm
    0.08
    Solver
    0.08
    Sparse
    0.08
     Sparse
    0.08
    acket
    0.07
     subroutine
    0.07
     sparse
    0.07
     Algorithms
    0.07
     solver
    0.07
    Activations Density 0.025%

    No Known Activations