© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3895
    Prev
    Next
    INDEX
    Explanations

    culture

    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
    个交æĺĵ
    -0.23
    ä½ıæĪ¿åħ¬ç§¯
    -0.22
    )((((
    -0.22
    hotmail
    -0.21
    ä¸īç§įèģĮä¸ļ
    -0.20
    'icon
    -0.20
    },č↵č↵
    -0.20
     Dota
    -0.20
     maman
    -0.19
    åĨ°æ·ĩ
    -0.19
    POSITIVE LOGITS
    åħ»
    0.28
    çݯå¢ĥ
    0.22
    åŁ¹åħ»
    0.22
    çĶŁéķ¿
    0.21
    æĿ¡ä»¶
    0.21
     environment
    0.20
     nurturing
    0.20
    gregar
    0.20
     conditions
    0.19
    ä¿Ŀåħ»
    0.19
    Activations Density 0.333%

    No Known Activations