© 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. 1328
    Prev
    Next
    INDEX
    Explanations

    section headers

    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
    ------+------+
    -0.29
    âļĹ
    -0.27
    ðŁĵIJ
    -0.25
    =-=-
    -0.24
    ãİľ
    -0.23
    bove
    -0.23
    schlie
    -0.23
    /vendors
    -0.23
    bsolute
    -0.23
     èĭ¥è¦ģ
    -0.23
    POSITIVE LOGITS
     Notes
    0.25
    åĩłçĤ¹
    0.25
     overview
    0.24
    æ¦ĤåĨµ
    0.23
    注æĦıäºĭ项
    0.23
    ä¸ĭéĿ¢å°±
    0.23
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.23
    ç»Ħç»ĩé¢Ĩ导
    0.22
    ##
    0.22
    ###
    0.22
    Activations Density 1.280%

    No Known Activations