© 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. 1112
    Prev
    Next
    INDEX
    Explanations

    industry and politics

    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
     libertine
    -0.33
    å±Ĥåĩºä¸į
    -0.32
     cuckold
    -0.31
    /effects
    -0.30
     erotica
    -0.28
     underrated
    -0.26
    /background
    -0.25
    -Semit
    -0.25
    ActivityIndicator
    -0.25
    ynos
    -0.25
    POSITIVE LOGITS
    è¿İåIJĪ
    0.27
     conveniently
    0.27
    åįĥæĸ¹çĻ¾è®¡
    0.26
     convenient
    0.24
    çĿĢåĬĽæīĵéĢł
    0.22
     manip
    0.22
    毫æĹł
    0.22
    .Usuario
    0.22
    æīĢè°ĵçļĦ
    0.22
     "'
    0.22
    Activations Density 3.698%

    No Known Activations