© 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. 3211
    Prev
    Next
    INDEX
    Explanations

    variety

    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
    ĵĺ
    -0.25
    SFML
    -0.25
     Böl
    -0.24
    usher
    -0.23
     Gorgeous
    -0.22
    çī¹ä»·
    -0.22
     jó
    -0.20
     spécialisé
    -0.20
    ç½ijé¦ĸ页
    -0.20
     acompaña
    -0.20
    POSITIVE LOGITS
    range
    0.22
    建档ç«ĭ
    0.21
    entanyl
    0.21
    .ReadByte
    0.21
    NullOr
    0.21
    /↵↵↵↵
    0.20
    UITextField
    0.20
    nqu
    0.20
    .sul
    0.20
    OnClickListener
    0.20
    Activations Density 0.269%

    No Known Activations