© 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. 3212
    Prev
    Next
    INDEX
    Explanations

    say "numbers"

    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
    (GLFW
    -0.23
     intimid
    -0.20
    岿
    -0.20
    =./
    -0.19
    cli
    -0.19
    lest
    -0.19
    عاÙħÙĦ
    -0.19
    ãĥµ
    -0.19
    æ©¡èĥ¶
    -0.18
    arity
    -0.18
    POSITIVE LOGITS
    个交æĺĵ
    0.27
    '].$
    0.23
    '].'/
    0.22
    beiter
    0.21
     Jetzt
    0.21
    InSeconds
    0.20
    黢
    0.20
    .Listen
    0.19
    lucent
    0.19
    PILE
    0.19
    Activations Density 0.021%

    No Known Activations