© 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. 1260
    Prev
    Next
    INDEX
    Explanations

    word 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
    ecided
    -0.25
    thinkable
    -0.24
    vably
    -0.22
    "<?
    -0.21
    _produk
    -0.21
     DbSet
    -0.21
    .scalablytyped
    -0.21
    .IsAny
    -0.21
     bénéficie
    -0.21
    )((((
    -0.21
    POSITIVE LOGITS
    ness
    0.66
    NESS
    0.49
    nes
    0.37
     enough
    0.36
     yet
    0.35
    ä¸Ķ
    0.35
    -looking
    0.32
    ç¨ĭ度
    0.31
     ness
    0.30
    ly
    0.29
    Activations Density 4.714%

    No Known Activations