© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3098
    Prev
    Next
    INDEX
    Explanations

    byMethod used: 1Reason: The MAX_ACTIVATING_TOKENS are overwhelmingly the word "by"

    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
    =".$_
    -0.21
    noinspection
    -0.20
     Ze
    -0.19
    PDOException
    -0.19
    WriteBarrier
    -0.19
    æĸ½çŃĸ
    -0.18
    å¹´ä¹ĭä¹ħ
    -0.18
    amo
    -0.17
    outline
    -0.17
     componentName
    -0.17
    POSITIVE LOGITS
    oriously
    0.23
    ÃŃpio
    0.23
     juxtap
    0.22
    ocial
    0.21
    .Fat
    0.21
    اسر
    0.21
    yat
    0.21
    mere
    0.21
    æī£
    0.21
    ERGY
    0.20
    Activations Density 0.360%

    No Known Activations