© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1484
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    .easing
    -0.23
    noinspection
    -0.23
    âģĥ
    -0.22
    SSERT
    -0.21
    çīĤ
    -0.21
    apiro
    -0.21
    åŀ§
    -0.21
     ofApp
    -0.21
     hely
    -0.21
    ãİİ
    -0.20
    POSITIVE LOGITS
    ÃĹ
    0.26
    =\"#
    0.23
    ptrdiff
    0.21
    oid
    0.21
     ÃĹ
    0.21
    说å¾Ĺ
    0.20
     domain
    0.20
    .InnerText
    0.20
    \t
    0.19
    大å°ı
    0.19
    Activations Density 0.396%

    No Known Activations