© 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. 2866
    Prev
    Next
    INDEX
    Explanations

    technical or program 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
    less
    -0.21
    æĸ¹éĿ¢çļĦ
    -0.20
     aspect
    -0.20
    fil
    -0.19
    éĽĨ
    -0.19
    伸åĩº
    -0.19
    侧ç»ĵæŀĦæĢ§
    -0.18
    _written
    -0.18
    slideUp
    -0.18
    no
    -0.18
    POSITIVE LOGITS
    BuilderInterface
    0.27
    .yy
    0.25
    ,");↵
    0.25
    :params
    0.24
    /GPL
    0.24
    -UA
    0.23
    -ln
    0.23
    .ibatis
    0.23
    );\↵
    0.22
    igidBody
    0.22
    Activations Density 1.246%

    No Known Activations