© 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. 259
    Prev
    Next
    INDEX
    Explanations

    client roles

    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
    rysler
    -0.28
    rvine
    -0.27
    tsy
    -0.26
    пиÑģÑĭва
    -0.26
    clusão
    -0.26
    ".↵↵↵↵
    -0.26
     Hã
    -0.26
    comings
    -0.25
    -Headers
    -0.25
    âļĹ
    -0.25
    POSITIVE LOGITS
    hood
    0.23
     dumpsters
    0.23
    ÑĤвеÑĢжда
    0.23
     athleticism
    0.23
    less
    0.23
    entanyl
    0.22
    -authored
    0.21
    neath
    0.21
    èĢĥãģĪæĸ¹
    0.20
    uchsia
    0.20
    Activations Density 8.680%

    No Known Activations