© 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. 3016
    Prev
    Next
    INDEX
    Explanations

    word fragments

    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
    ï¼ģ",
    -0.23
    FTER
    -0.22
    èĵĬ
    -0.21
     potrÃł
    -0.21
     valido
    -0.20
    дÑĢеÑģ
    -0.20
     Erect
    -0.19
     équipé
    -0.19
    ï¼ļ"+
    -0.19
    ps
    -0.19
    POSITIVE LOGITS
    ampie
    0.23
    commended
    0.23
    linky
    0.23
    uards
    0.23
    abbo
    0.23
    xima
    0.22
    ByPrimaryKey
    0.22
    Wunused
    0.22
    azard
    0.22
    alette
    0.22
    Activations Density 0.027%

    No Known Activations