© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 752
    Prev
    Next
    INDEX
    Explanations

    dollar sign

    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
    orris
    -0.23
    orgh
    -0.21
    ennifer
    -0.21
    تÙĦÙĥ
    -0.21
     dem
    -0.21
    -0.21
    inspace
    -0.20
    ottage
    -0.20
     gql
    -0.20
    rouw
    -0.20
    POSITIVE LOGITS
    íĶĦë¡ľê·¸
    0.29
    æľĭåıĭ们对
    0.27
     indeb
    0.26
    GLOBALS
    0.26
     çĶŁåij½åij¨æľŁ
    0.25
    iards
    0.24
     POLITICO
    0.24
     testim
    0.23
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.23
    )prepare
    0.22
    Activations Density 0.263%

    No Known Activations