© 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. 988
    Prev
    Next
    INDEX
    Explanations

    e

    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
    lève
    -0.22
     appare
    -0.20
     однако
    -0.20
     tuy
    -0.19
     %+
    -0.18
    ìĺ´
    -0.18
    #undef
    -0.18
     extern
    -0.18
    çĽ¸ä¿¡å¤§å®¶
    -0.18
     unst
    -0.18
    POSITIVE LOGITS
    ollapsed
    0.23
    itizen
    0.23
    Gratis
    0.22
    .openConnection
    0.22
    byss
    0.22
    æ±Ĩ
    0.22
    -ie
    0.21
    zych
    0.21
    :Add
    0.21
    ynchronously
    0.21
    Activations Density 0.556%

    No Known Activations