© 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. 1147
    Prev
    Next
    INDEX
    Explanations

    SQL queries

    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
    /MIT
    -0.22
    女æĢ§æľĭåıĭ
    -0.21
    odore
    -0.21
    IGHLIGHT
    -0.21
    DDevice
    -0.20
     loadChildren
    -0.20
     çĶŁåij½åij¨æľŁ
    -0.20
     èĩªåĬ¨çĶŁæĪIJ
    -0.19
    estruction
    -0.19
    ynamo
    -0.19
    POSITIVE LOGITS
    iente
    0.21
    deb
    0.20
    çIJİ
    0.20
     sca
    0.19
    æ®ļ
    0.19
     Scrolls
    0.19
    åī¿
    0.19
    æĿ¨æ¬¢
    0.18
    翾
    0.18
     hvad
    0.18
    Activations Density 0.001%

    No Known Activations