© 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. 745
    Prev
    Next
    INDEX
    Explanations

    unusual characters

    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
     hmm
    -0.22
    gnore
    -0.20
    .');č↵
    -0.20
    doch
    -0.19
    ucursal
    -0.19
    .');
    -0.19
    åĵĩ
    -0.19
    å²ģæŶ
    -0.18
    emento
    -0.18
    å¥ĸåѦ
    -0.18
    POSITIVE LOGITS
    /Dk
    0.33
    !
    0.31
    并ä¸įæĺ¯å¾Ī
    0.29
    ï¼ģ
    0.25
    éĥ¨åī¯
    0.22
    à¤ij
    0.22
    	mysqli
    0.22
    OUNDS
    0.22
    'email
    0.21
    æĩij
    0.21
    Activations Density 1.929%

    No Known Activations