© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1979
    Prev
    Next
    INDEX
    Explanations

    business strategy

    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
    产åѦ
    -0.33
     entreprene
    -0.27
    çŀŁ
    -0.26
    åºĶæĶ¶è´¦
    -0.25
    ç±¼
    -0.24
    æıŃæĻĵ
    -0.24
     crowdfunding
    -0.24
    çļĦæ¨¡æł·
    -0.24
    游æĪıæĬĢå·§
    -0.24
    èĪ¯
    -0.24
    POSITIVE LOGITS
    -widgets
    0.35
    -toast
    0.34
     fierc
    0.32
    女æĢ§æľĭåıĭ
    0.32
     ());↵↵
    0.32
     dikke
    0.31
    -await
    0.31
    -translate
    0.30
    é³ħ
    0.30
     bigot
    0.30
    Activations Density 8.374%

    No Known Activations