© 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. 2770
    Prev
    Next
    INDEX
    Explanations

    page or chapter

    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
    Ū
    -0.21
    моÑĤ
    -0.20
    ostringstream
    -0.20
    avanaugh
    -0.19
    วà¸Ķ
    -0.19
    zoek
    -0.19
    itin
    -0.19
    .centerY
    -0.19
    ATYPE
    -0.19
    Ũ
    -0.19
    POSITIVE LOGITS
     Page
    0.28
    grily
    0.26
    .page
    0.24
    page
    0.24
    Page
    0.23
    www
    0.23
    olume
    0.22
    .tech
    0.21
    -page
    0.21
     Chapter
    0.21
    Activations Density 0.065%

    No Known Activations