© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1479
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    crast
    -0.28
    )(((
    -0.24
    pisa
    -0.24
    ÑĢенд
    -0.23
    ¡´
    -0.22
    rchive
    -0.22
    ughs
    -0.22
    кÑĢÑĭл
    -0.22
     nederland
    -0.22
    iddle
    -0.22
    POSITIVE LOGITS
    ISTRIBUT
    0.27
    ImageButton
    0.23
    ighborhood
    0.23
     york
    0.21
    verständlich
    0.20
    iaux
    0.20
    riott
    0.19
    phalt
    0.19
    ASHINGTON
    0.19
    Wenn
    0.19
    Activations Density 0.880%

    No Known Activations