© 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
    2. Qwen2.5-7B-IT
    3. 20-MATRYOSHKA-65K
    4. 460
    Prev
    Next
    INDEX
    Explanations

    headlines and titles

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :^
    -0.21
    ');");↵
    -0.21
     ');
    -0.21
    éĤ´
    -0.20
    vtk
    -0.20
    [++
    -0.20
    []{↵
    -0.20
    abcdefghijkl
    -0.19
    ANDOM
    -0.19
    èĿ®
    -0.19
    POSITIVE LOGITS
     "','
    0.21
     dual
    0.19
    èĵī
    0.19
    Neal
    0.18
     ['./
    0.18
    здание
    0.18
    æĦŁåħ´è¶£çļĦ
    0.18
     rects
    0.18
     italiane
    0.18
    æĸ°éĹ»ä¸Ńå¿ĥ
    0.18
    Activations Density 0.009%

    No Known Activations