© 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. 867
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    <fieldset
    -0.31
    ASHINGTON
    -0.21
    arrants
    -0.20
    oline
    -0.19
    ç½´
    -0.19
    hamster
    -0.19
    lish
    -0.19
    ano
    -0.19
    Feels
    -0.18
    byss
    -0.18
    POSITIVE LOGITS
    åı¹äºĨåı£æ°Ķ
    0.25
    uellement
    0.23
     whiteColor
    0.21
     Suche
    0.21
    æijĩäºĨæijĩ头
    0.20
    StrictEqual
    0.20
     (>
    0.20
     blackColor
    0.20
    è¸Ķ
    0.19
    女åħĴ
    0.19
    Activations Density 1.113%

    No Known Activations