© 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. 2713
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    åĤį
    -0.21
    æ´»
    -0.21
    é£Łãģ¹ãģ¦
    -0.21
     libero
    -0.20
    Ñģан
    -0.20
     MASS
    -0.20
    _firestore
    -0.19
    以åIJİ
    -0.19
    (/^\
    -0.19
    stinian
    -0.19
    POSITIVE LOGITS
    .useState
    0.22
    <![
    0.21
    .viewport
    0.19
     jihadist
    0.19
    ,},↵
    0.19
    traî
    0.19
     Strom
    0.18
     ($("#
    0.18
    .notNull
    0.18
    /inet
    0.18
    Activations Density 0.001%

    No Known Activations