© 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. 1408
    Prev
    Next
    INDEX
    Explanations

    hardware access and registers

    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
     maneu
    -0.29
    æ³ķå¸ĪèģĮä¸ļ
    -0.28
    -toggler
    -0.25
    çݩ家æľĭåıĭ
    -0.25
    èĪ¯
    -0.24
    apons
    -0.24
     safezone
    -0.24
    _YUV
    -0.24
    _RCC
    -0.24
    æĪĺ士æĿ¥è¯´
    -0.24
    POSITIVE LOGITS
    æĶ»åĩ»åĬĽ
    0.27
     cigaret
    0.26
     memcpy
    0.23
    éĢ»è¾ij
    0.23
    è¿Ļ个èģĮä¸ļ
    0.23
    -elected
    0.23
    	strncpy
    0.22
    oen
    0.22
     strncpy
    0.22
     advoc
    0.21
    Activations Density 3.316%

    No Known Activations