© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3427
    Prev
    Next
    INDEX
    Explanations

    abbreviations

    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
    feof
    -0.27
    eldom
    -0.23
    ;?>"
    -0.21
    |min
    -0.21
    |unique
    -0.20
    enden
    -0.20
    Ắ
    -0.20
    Ê·
    -0.20
    .Matchers
    -0.19
     ><?
    -0.18
    POSITIVE LOGITS
    usterity
    0.26
    QDebug
    0.22
    ><?=$
    0.21
    ssue
    0.20
     cellForRowAt
    0.20
     Retrie
    0.20
     Buster
    0.19
    æĥľ
    0.19
     Metallic
    0.19
     LTD
    0.19
    Activations Density 0.010%

    No Known Activations