© 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. 626
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    ágenes
    -0.23
    ÙħÙĤاÙĦات
    -0.20
    åİ¥
    -0.19
    æīĭæľºçīĪ
    -0.19
     UIStoryboard
    -0.18
     Kathy
    -0.18
    æĿ¨å¹Ĥ
    -0.18
    'options
    -0.18
    Usage
    -0.18
    quiet
    -0.18
    POSITIVE LOGITS
    itag
    0.23
    :`~
    0.23
     Müsl
    0.23
    leanor
    0.22
    pgsql
    0.22
     Parenthood
    0.21
    GenericType
    0.21
    &);↵↵
    0.21
    lijah
    0.21
    roit
    0.21
    Activations Density 0.002%

    No Known Activations