© 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. 737
    Prev
    Next
    INDEX
    Explanations

    haveMethod used: 1

    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
     activeClassName
    -0.22
    achie
    -0.21
    usk
    -0.20
     conte
    -0.20
     present
    -0.20
    dÃŃ
    -0.20
     LIABLE
    -0.20
    axies
    -0.19
    -purple
    -0.19
    ate
    -0.19
    POSITIVE LOGITS
     been
    0.47
    htag
    0.41
    been
    0.38
    htags
    0.33
    ometown
    0.33
    htable
    0.32
    Been
    0.31
    :';↵
    0.30
    indsight
    0.28
    BeenCalled
    0.27
    Activations Density 1.229%

    No Known Activations