© 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. 1546
    Prev
    Next
    INDEX
    Explanations

    code and names

    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
    phalt
    -0.24
    avanaugh
    -0.24
     ((__
    -0.24
    mouseleave
    -0.23
    ocre
    -0.23
    åĭł
    -0.23
    -Trump
    -0.22
    endencies
    -0.22
     (*((
    -0.22
     addCriterion
    -0.21
    POSITIVE LOGITS
    åŃĢ
    0.22
    è¿ĶåĽŀæIJľçĭIJ
    0.22
    ulumi
    0.20
     BinaryTree
    0.20
    .='
    0.20
    _simps
    0.20
    íĿĺ
    0.20
    ä¹Įåħĭ
    0.20
    åħħè£ķ
    0.20
    chedulers
    0.19
    Activations Density 0.751%

    No Known Activations