© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 143
    Prev
    Next
    INDEX
    Explanations

    =

    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
    abyrin
    -0.30
    å¤įå·¥å¤į
    -0.29
    ombine
    -0.27
     fiance
    -0.27
    abcdefghijkl
    -0.26
     bergen
    -0.26
    scrição
    -0.26
    ãĥµ
    -0.25
    .Sqrt
    -0.24
     molec
    -0.23
    POSITIVE LOGITS
    /=
    0.31
    èħĺ
    0.24
    %"><
    0.24
    ities
    0.21
    æľºä½ĵ
    0.21
    骶
    0.21
     güzel
    0.21
     “
    0.20
     a
    0.20
    è¿Ļä¹Ī
    0.20
    Activations Density 0.544%

    No Known Activations