© 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. 917
    Prev
    Next
    INDEX
    Explanations

    technical symbols

    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
    },{↵
    -0.29
     LOWER
    -0.20
     ".↵
    -0.20
    æķ¢
    -0.19
    xeb
    -0.19
    _translation
    -0.19
     Ook
    -0.19
    ABSPATH
    -0.19
     CONDITIONS
    -0.18
    éģĴ
    -0.18
    POSITIVE LOGITS
    aeda
    0.27
    intage
    0.21
    .ManyToMany
    0.20
    éķ¦
    0.18
    (ERR
    0.18
    atory
    0.18
    memberOf
    0.18
    讯
    0.18
    .AdapterView
    0.18
    stro
    0.18
    Activations Density 0.002%

    No Known Activations