© 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. 1286
    Prev
    Next
    INDEX
    Explanations

    unknown script

    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
    :;↵
    -0.23
    zap
    -0.22
    /ay
    -0.22
    anse
    -0.21
    %;"
    -0.21
     beneficiation
    -0.21
    ETCH
    -0.21
     misdemean
    -0.20
    /*↵
    -0.20
    urgent
    -0.20
    POSITIVE LOGITS
    è¿Ļä¹Īå¤ļ
    0.48
    å¦ĤæѤ
    0.44
    è¿Ļä¹Ī
    0.41
    è¿Ļä¹Ī大
    0.37
    å±ħçĦ¶
    0.35
     suddenly
    0.35
    è¿Ļæł·ä¸Ģ个
    0.33
    éĤ£ä¹Īå¤ļ
    0.32
     such
    0.32
    éĢĻ麼
    0.31
    Activations Density 3.463%

    No Known Activations