© 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. 3866
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    BaseContext
    -0.24
    ;]/
    -0.20
    ä¸įåĬ¨
    -0.20
     HtmlWebpackPlugin
    -0.19
    shortcut
    -0.19
    rippling
    -0.19
    (Return
    -0.19
    åīįæīĢ
    -0.18
     actionTypes
    -0.18
    urons
    -0.18
    POSITIVE LOGITS
    ('@/
    0.24
    ãĥĭãĤ¢
    0.23
    -transitional
    0.22
    okia
    0.21
    ibal
    0.20
     clearColor
    0.20
    omp
    0.20
    ãİı
    0.19
    riority
    0.19
    erguson
    0.19
    Activations Density 0.041%

    No Known Activations