© 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. 318
    Prev
    Next
    INDEX
    Explanations

    require

    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
    éŃĶæ³ķå¸ĪåĴĮ
    -0.28
    æľīåĬ©
    -0.24
    ä»Ģä¹Īéĥ½ä¸į
    -0.24
    $LANG
    -0.24
    æĹłæīĢè°ĵ
    -0.23
    wyn
    -0.22
    æĩĴå¾Ĺ
    -0.22
    errMsg
    -0.22
    æľĢåŁºæľ¬
    -0.21
    æ³ķå¸ĪèģĮä¸ļ
    -0.21
    POSITIVE LOGITS
     require
    0.37
     requires
    0.36
    å¾Īéļ¾
    0.34
     requiring
    0.31
    éļ¾ä»¥
    0.30
    è¦ģæ±Ĥ
    0.28
     required
    0.28
    æ¯ķç«Ł
    0.28
    Requires
    0.27
     пÑĢидеÑĤÑģÑı
    0.27
    Activations Density 4.962%

    No Known Activations