© 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. 1284
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    '=>['
    -0.23
    é¦Ĭ
    -0.20
    åķģ
    -0.20
    /thumb
    -0.19
    ([]*
    -0.19
    \application
    -0.19
    gunakan
    -0.19
    etrofit
    -0.19
    .RadioButton
    -0.18
    ç»ıèIJ¥çIJĨ念
    -0.18
    POSITIVE LOGITS
     ontvang
    0.22
    ouflage
    0.21
    udd
    0.21
    èĶĵ
    0.21
     burge
    0.19
     cheats
    0.19
    endencies
    0.18
    æºŁ
    0.18
    CKER
    0.18
    @Module
    0.18
    Activations Density 0.002%

    No Known Activations