© 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. 41
    Prev
    Next
    INDEX
    Explanations

    He

    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
    å«ģç»Ļ
    -0.28
     itself
    -0.27
     коÑĤоÑĢое
    -0.27
    å«ģ
    -0.25
    ÑĪло
    -0.24
    Its
    -0.23
    å¨ĺ家
    -0.23
    让å®ĥ
    -0.23
    venue
    -0.23
    å®ĥçļĦ
    -0.22
    POSITIVE LOGITS
     himself
    1.01
     his
    0.81
    åĴĮä»ĸçļĦ
    0.77
    his
    0.74
    ä»ĸçļĦ
    0.73
    äºĨä»ĸçļĦ
    0.60
    åľ¨ä»ĸçļĦ
    0.53
     Himself
    0.53
    å½ĵä»ĸ
    0.49
    ä»ĸèĩªå·±
    0.48
    Activations Density 4.784%

    No Known Activations