© 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. 642
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    /lg
    -0.29
    æµģæ°ĵ
    -0.28
    /fw
    -0.25
    /ay
    -0.24
    ï¿ł
    -0.24
    /watch
    -0.24
     intimidate
    -0.24
    ÎĻ
    -0.23
    -REAL
    -0.23
     intimid
    -0.23
    POSITIVE LOGITS
    æĪĺ士æĿ¥è¯´
    0.45
    æľĭåıĭ们对
    0.35
     )↵↵↵↵↵↵↵↵
    0.35
    éŃĶæ³ķå¸ĪåĴĮ
    0.35
     Interracial
    0.34
    .IsNullOr
    0.31
    åĩ¡æľ¬ç½ij
    0.30
    èĻİåį«
    0.30
     cosplay
    0.30
     Millenn
    0.29
    Activations Density 13.771%

    No Known Activations