© 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. 1138
    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
    ByPrimaryKey
    -0.21
     afs
    -0.20
    иÑĢÑĥÑİÑĤ
    -0.19
    æķĿ
    -0.19
    еÑĩно
    -0.19
    ButtonModule
    -0.18
     perchè
    -0.18
     Vuex
    -0.18
     remix
    -0.18
     DXGI
    -0.18
    POSITIVE LOGITS
    -Cs
    0.24
    ãİĿ
    0.24
    redient
    0.23
    éģĴ
    0.22
    -valu
    0.22
    strstr
    0.22
    setVisibility
    0.21
    èģĴ
    0.21
    prung
    0.21
    æĤĴ
    0.21
    Activations Density 0.009%

    No Known Activations