© 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. 18
    Prev
    Next
    INDEX
    Explanations

    vehicles and parts

    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
    ="<<
    -0.28
    诬
    -0.26
    âĪī
    -0.25
     ifndef
    -0.25
    è¯Ĥ
    -0.25
    æĪĺ士æĿ¥è¯´
    -0.25
    踺
    -0.24
    å¤įåį°
    -0.23
    ãĪ
    -0.23
    ($('<
    -0.23
    POSITIVE LOGITS
    æĢ§ä»·
    0.31
    âļĹ
    0.30
    ;break
    0.27
    -NLS
    0.27
    ËĤ
    0.27
    +-+-
    0.27
    æIJŃè½½
    0.27
    ç´łæĻ´
    0.26
    ðŁĵIJ
    0.26
    建档ç«ĭ
    0.25
    Activations Density 4.368%

    No Known Activations