© 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. 210
    Prev
    Next
    INDEX
    Explanations

    measurements and numbers

    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
    åħļæĢ»
    -0.23
    ysqli
    -0.21
    inz
    -0.21
    illard
    -0.20
    );$
    -0.20
    nqu
    -0.20
    :invoke
    -0.19
     kald
    -0.19
    imdi
    -0.19
    opup
    -0.19
    POSITIVE LOGITS
    ilet
    0.20
    its
    0.20
    ilee
    0.20
     türlü
    0.19
     Hat
    0.19
    íĶĦë¡ľê·¸
    0.19
    .ElementAt
    0.19
    č↵↵
    0.19
    ceb
    0.18
    CMP
    0.18
    Activations Density 0.278%

    No Known Activations