© 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. 1434
    Prev
    Next
    INDEX
    Explanations

    scientific suffixes

    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
    oneksi
    -0.26
    ooter
    -0.22
    ombat
    -0.21
    avors
    -0.21
    omite
    -0.21
     Rohing
    -0.20
    reon
    -0.20
    /reset
    -0.20
    serter
    -0.20
    upert
    -0.20
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.30
    ally
    0.29
    ically
    0.28
    ALLY
    0.28
    -based
    0.26
     dikke
    0.26
    ized
    0.25
    ìłģìľ¼ë¡ľ
    0.23
    illy
    0.22
    ographically
    0.22
    Activations Density 7.523%

    No Known Activations