© 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. 553
    Prev
    Next
    INDEX
    Explanations

    sqrt

    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
    .vertx
    -0.21
     jihadist
    -0.21
    é½ģ
    -0.20
    å¿į
    -0.20
     WrocÅĤaw
    -0.18
    嵯
    -0.18
    ç²¾åĬĽ
    -0.18
    ç§ijçłĶéĻ¢
    -0.18
    æł¼
    -0.18
     franç
    -0.18
    POSITIVE LOGITS
    >'.↵
    0.25
    >\<
    0.23
    kits
    0.22
    asjon
    0.21
    Periph
    0.20
    åĽ«
    0.20
    ivité
    0.20
    .toHexString
    0.20
    ilogy
    0.20
    :variables
    0.20
    Activations Density 0.177%

    No Known Activations