© 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. 3979
    Prev
    Next
    INDEX
    Explanations

    specific entries

    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
     MetroFramework
    -0.27
    foundland
    -0.27
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.23
     potrÃł
    -0.23
    enegro
    -0.23
    stdafx
    -0.23
    .writerow
    -0.22
     addCriterion
    -0.22
    ãİı
    -0.21
     ()->
    -0.21
    POSITIVE LOGITS
    wis
    0.21
    lov
    0.20
    oxetine
    0.20
    èīı
    0.19
    kir
    0.19
    owa
    0.19
    uto
    0.19
    ulan
    0.18
    oji
    0.18
    éľ²
    0.18
    Activations Density 0.010%

    No Known Activations