© 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. 3252
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
     Dabei
    -0.23
    ãĤĭãģ¹ãģį
    -0.20
     AuÃŁerdem
    -0.20
    ç¼±
    -0.20
    istingu
    -0.20
    æĹłè®ºæĺ¯åħ¶
    -0.19
    Sony
    -0.19
    :bold
    -0.19
    /latest
    -0.19
    indsay
    -0.18
    POSITIVE LOGITS
     Pistons
    0.22
     Incontri
    0.22
    baugh
    0.21
    icorn
    0.21
    .liferay
    0.21
    irlines
    0.20
    umbing
    0.20
     QLD
    0.20
    ovsky
    0.20
    />\
    0.20
    Activations Density 0.690%

    No Known Activations