© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3382
    Prev
    Next
    INDEX
    Explanations

    opinions and people

    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
     gó
    -0.22
    ToUpper
    -0.21
    íĶĦë¡ľê·¸
    -0.20
    ToLower
    -0.20
    ellar
    -0.19
    黩
    -0.19
    endedor
    -0.19
    @student
    -0.19
    -init
    -0.19
    zcze
    -0.19
    POSITIVE LOGITS
     him
    0.45
    çľĭä»ĸ
    0.43
    对ä»ĸ
    0.41
    ä»ĸçļĦ
    0.41
     his
    0.41
    æĬĬä»ĸ
    0.40
    ç»Ļä»ĸ
    0.35
    ä»ĸæĺ¯ä¸Ģ个
    0.35
    ä»ĸæĺ¯
    0.34
    对åħ¶
    0.34
    Activations Density 0.830%

    No Known Activations