© 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. 1767
    Prev
    Next
    INDEX
    Explanations

    definition

    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
    omanip
    -0.25
    .Monad
    -0.23
    âĢ½
    -0.23
     getById
    -0.22
    rio
    -0.22
    ;br
    -0.22
    gebn
    -0.21
    è¿Ļ款车
    -0.21
    ;display
    -0.21
     Palestin
    -0.21
    POSITIVE LOGITS
    å®ļä¹ī
    0.59
     definition
    0.57
     Definition
    0.50
     definitions
    0.48
    definition
    0.47
    Definition
    0.47
    æ¦Ĥ念
    0.44
    çķĮå®ļ
    0.42
    -definition
    0.42
     term
    0.41
    Activations Density 4.557%

    No Known Activations