© 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. 986
    Prev
    Next
    INDEX
    Explanations

    technical notation

    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
    rigesimal
    -0.28
    çŀł
    -0.22
    éĵIJ
    -0.20
    à¹ģละà¸Ħวาม
    -0.20
    ç§ī
    -0.19
    éĩįè¦ģåİŁåĽł
    -0.19
     ìĿ´ê²ĥìĿĢ
    -0.18
    åıĭæĥħéĵ¾æİ¥
    -0.18
    nesty
    -0.18
    ERRU
    -0.18
    POSITIVE LOGITS
    /=
    0.26
    ornment
    0.25
    foundland
    0.24
    ){}↵
    0.23
    -fw
    0.23
    [out
    0.22
     .↵↵↵↵
    0.22
    /from
    0.21
    /of
    0.21
     cornerback
    0.21
    Activations Density 1.433%

    No Known Activations