© 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. 157
    Prev
    Next
    INDEX
    Explanations

    academic 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
     PhpStorm
    -0.28
    -initialized
    -0.27
    aeda
    -0.27
    .Imaging
    -0.27
    YPD
    -0.24
    addir
    -0.24
    lassian
    -0.23
    mouseout
    -0.23
    /li
    -0.23
    stdarg
    -0.23
    POSITIVE LOGITS
    åıĸåĨ³
    0.20
     =>'
    0.20
     J
    0.20
    .subscriptions
    0.20
    aa
    0.20
    S
    0.19
     incontr
    0.19
    ä»Ģ麽
    0.19
    éĢĤåIJĪèĩªå·±
    0.19
    IS
    0.18
    Activations Density 0.213%

    No Known Activations