© 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. 457
    Prev
    Next
    INDEX
    Explanations

    code operations

    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
    æ°²
    -0.25
     fiance
    -0.24
    å·¥ä½ľæľºåĪ¶
    -0.23
    çĶŁæĢģåľĪ
    -0.22
    å¤©åĽ½
    -0.22
    æŁIJ个
    -0.22
    æĥ«
    -0.22
    .bmp
    -0.21
    åĢ¥
    -0.21
    åĺŀ
    -0.21
    POSITIVE LOGITS
     :";↵
    0.37
    printStats
    0.29
    ṡ
    0.28
     MediaTek
    0.28
    çļĦ带é¢Ĩ
    0.28
    /goto
    0.27
    ç°ī
    0.27
    ï¬Ħ
    0.26
    :".$
    0.26
    :'.$
    0.26
    Activations Density 0.015%

    No Known Activations