© 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. 1140
    Prev
    Next
    INDEX
    Explanations

    include guard

    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
    æŁ¥çľĭ详æĥħ
    -0.35
     CORPOR
    -0.32
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.32
    -REAL
    -0.30
    ffield
    -0.30
    æijĩäºĨ
    -0.29
     GOODS
    -0.28
    TEMPL
    -0.27
     çĶŁåij½åij¨æľŁ
    -0.27
     INCIDENT
    -0.26
    POSITIVE LOGITS
    .COM
    0.26
     reelection
    0.26
     }}"><
    0.25
    IN
    0.23
     '~/
    0.22
    AL
    0.22
    iore
    0.22
    adan
    0.22
    _P
    0.22
     totalPrice
    0.22
    Activations Density 2.678%

    No Known Activations