© 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. 2733
    Prev
    Next
    INDEX
    Explanations

    while

    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
    É¡
    -0.21
    solete
    -0.21
    éķ«
    -0.20
    -aos
    -0.20
     wen
    -0.20
    Thêm
    -0.20
    abyrin
    -0.19
     Usuarios
    -0.19
    StackSize
    -0.19
    -yyyy
    -0.19
    POSITIVE LOGITS
    /Internal
    0.31
     nuest
    0.31
    âĮĪ
    0.29
    /Instruction
    0.27
    .IsNullOr
    0.27
    สามาร
    0.25
    (*)(
    0.24
     simultaneously
    0.24
    s
    0.23
    /GL
    0.23
    Activations Density 0.097%

    No Known Activations