© 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. 1582
    Prev
    Next
    INDEX
    Explanations

    settings

    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
     enthus
    -0.25
     Según
    -0.21
    lijah
    -0.21
     één
    -0.20
    ä»ħ代表
    -0.20
     ErdoÄŁan
    -0.19
     lesbienne
    -0.19
    æķ´çIJĨ
    -0.19
    ossa
    -0.19
    å°´å°¬
    -0.19
    POSITIVE LOGITS
    设置
    0.42
     settings
    0.39
     设置
    0.37
     setting
    0.37
    è¨Ńå®ļ
    0.35
     Setting
    0.33
    设å®ļ
    0.31
     ìĦ¤ìłķ
    0.30
     options
    0.30
    éĢī项
    0.30
    Activations Density 2.998%

    No Known Activations