© 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. 1123
    Prev
    Next
    INDEX
    Explanations

    Greek letters

    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
    èijŃ
    -0.22
    æľĪ
    -0.21
    akedown
    -0.20
    ../../../../
    -0.19
    ournemouth
    -0.19
    ä¸įäºĨ
    -0.19
    åijĥ
    -0.19
    jured
    -0.19
    ведение
    -0.19
    äºĮ级
    -0.19
    POSITIVE LOGITS
     fkk
    0.32
    åľ¨çݩ家
    0.30
     modalitÃł
    0.29
    íĶĦë¡ľê·¸
    0.27
     newPosition
    0.27
    åı¯ä»¥æĽ´å¥½
    0.27
    bilité
    0.26
    æĹłè®ºæĺ¯åħ¶
    0.25
    prar
    0.25
    并ä¸įæĦıåij³
    0.25
    Activations Density 0.521%

    No Known Activations