© 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. 724
    Prev
    Next
    INDEX
    Explanations

    say "I" or "me"

    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
     "('
    -0.29
    Ặ
    -0.22
    .infinity
    -0.22
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.21
    polator
    -0.21
    .SuppressLint
    -0.21
     Aydın
    -0.20
    ánÃŃ
    -0.20
    crollView
    -0.20
     lineWidth
    -0.20
    POSITIVE LOGITS
    æĪij们
    0.55
    æĪij
    0.52
    æĪij们çļĦ
    0.49
     we
    0.47
    æĪijåĢij
    0.46
    æĪijçļĦ
    0.45
     me
    0.44
    æĪijåĴĮ
    0.44
     my
    0.44
     you
    0.44
    Activations Density 5.078%

    No Known Activations