© 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. 1167
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    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
    æģĻ
    -0.22
    orgeous
    -0.21
     nto
    -0.20
    ISIBLE
    -0.19
     createSelector
    -0.19
     rico
    -0.19
    gewater
    -0.19
    çļĦ带é¢Ĩ
    -0.19
     resil
    -0.19
    ä¹Łä¸įéĶĻ
    -0.19
    POSITIVE LOGITS
     (*)(
    0.20
    .ReadAll
    0.20
    âĦħ
    0.20
    caff
    0.19
     AppBundle
    0.19
    'action
    0.19
    ture
    0.19
    ody
    0.19
    ,'\
    0.19
    abhängig
    0.18
    Activations Density 0.183%

    No Known Activations