© 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. 629
    Prev
    Next
    INDEX
    Explanations

    for/regarding

    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
    ĵåIJį
    -0.25
    éļĨéĩį举è¡Į
    -0.25
    postalcode
    -0.24
    éĩįè¦ģåĽłç´ł
    -0.24
    _REFERER
    -0.23
    iferay
    -0.22
    memberof
    -0.22
     companyName
    -0.21
    /Dk
    -0.21
     prostit
    -0.20
    POSITIVE LOGITS
     for
    0.56
     regarding
    0.55
    对äºİ
    0.50
    åħ³äºİ
    0.49
    	for
    0.48
    for
    0.48
     длÑı
    0.45
     untuk
    0.40
    à¹ĥà¸Ļà¸ģาร
    0.40
     Regarding
    0.37
    Activations Density 9.092%

    No Known Activations