© 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. 1325
    Prev
    Next
    INDEX
    Explanations

    questions and surveys

    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
     roma
    -0.28
    :;↵
    -0.27
    **)&
    -0.24
     **)&
    -0.23
    ﹤
    -0.22
    unread
    -0.21
    æŁ¥çľĭ详æĥħ
    -0.21
    女æĢ§æľĭåıĭ
    -0.21
    ampionship
    -0.21
    weeted
    -0.21
    POSITIVE LOGITS
    å¡«åĨĻ
    0.32
    éĹ®åį·
    0.32
     question
    0.32
     questions
    0.32
     questionnaire
    0.30
    å¡«
    0.29
    çŃĶé¢ĺ
    0.28
    éĹ®
    0.28
     asked
    0.28
    å¾ģéĽĨ
    0.28
    Activations Density 2.744%

    No Known Activations