© 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. 1788
    Prev
    Next
    INDEX
    Explanations

    0

    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
    ahlen
    -0.21
    _latest
    -0.19
    .setVertical
    -0.19
    [href
    -0.18
     Quar
    -0.18
    лим
    -0.18
    irmware
    -0.18
    ±
    -0.18
    endet
    -0.18
    isan
    -0.18
    POSITIVE LOGITS
    =zeros
    0.21
    -strong
    0.20
    $__
    0.20
     Jens
    0.20
    \grid
    0.20
    /Dk
    0.19
    汤
    0.19
    ä¹ĸä¹ĸ
    0.19
    $log
    0.18
    utherland
    0.18
    Activations Density 0.126%

    No Known Activations