© 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. 3747
    Prev
    Next
    INDEX
    Explanations

    technical and product terms

    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
    благо
    -0.25
    ãĦ§
    -0.23
    .MaximizeBox
    -0.21
     Åģa
    -0.20
    åħ¨èµĦåŃIJ
    -0.20
    поÑĤенÑĨи
    -0.20
    .myapplication
    -0.20
    serter
    -0.20
    è£ħå¤ĩåĪ¶éĢł
    -0.20
    åIJįåĪĹåīį
    -0.19
    POSITIVE LOGITS
    gnore
    0.27
    \controllers
    0.23
    celain
    0.21
    acle
    0.21
    curacy
    0.21
    alore
    0.20
     ÑģенÑĤ
    0.20
    nty
    0.20
    eah
    0.19
    ÅĤÄĻ
    0.19
    Activations Density 0.001%

    No Known Activations