© 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. 696
    Prev
    Next
    INDEX
    Explanations

    do

    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
    paralleled
    -0.27
    roleId
    -0.23
    oggler
    -0.23
     jihadists
    -0.23
     jihadist
    -0.21
    precedented
    -0.21
     ",");↵
    -0.21
    forgettable
    -0.20
    endencies
    -0.20
     '-')↵
    -0.19
    POSITIVE LOGITS
    ctest
    0.34
     Ukr
    0.28
    CLU
    0.26
    TECTED
    0.25
    WISE
    0.25
     indeed
    0.24
    ENCHMARK
    0.24
    ctype
    0.24
    âĸ¹
    0.24
    .navigationItem
    0.23
    Activations Density 0.718%

    No Known Activations