© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3847
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    :<?
    -0.24
     fkk
    -0.23
    çݩ家æľĭåıĭ
    -0.23
     initWithNibName
    -0.23
    []{↵
    -0.23
    .fromRGBO
    -0.22
     Ø£ÙģرÙĬ
    -0.22
    }elseif
    -0.22
     }}"><
    -0.21
    -toggler
    -0.21
    POSITIVE LOGITS
    讪
    0.21
    å¡ŀå°Ķ
    0.20
    äºĨåįĬ天
    0.19
     Han
    0.19
    emax
    0.19
     decltype
    0.18
    æīİæł¹
    0.18
    letal
    0.18
    ä¸Ģç±»
    0.18
    .postMessage
    0.18
    Activations Density 0.000%

    No Known Activations