© 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. 1092
    Prev
    Next
    INDEX
    Explanations

    word focus

    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
    extrême
    -0.22
    otros
    -0.21
    orgetown
    -0.21
    strcasecmp
    -0.20
    \OptionsResolver
    -0.20
     "-";↵
    -0.20
    izzato
    -0.20
     whiteColor
    -0.20
     blackColor
    -0.20
    âĺŁ
    -0.20
    POSITIVE LOGITS
    -specific
    0.32
    -related
    0.30
    -centric
    0.23
     móc
    0.23
    atego
    0.22
    opleft
    0.22
    :"-"`↵
    0.21
    -wide
    0.21
    <?>>
    0.20
    gart
    0.19
    Activations Density 9.999%

    No Known Activations