© 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. 940
    Prev
    Next
    INDEX
    Explanations

    parts

    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
     Kardash
    -0.25
    orWhere
    -0.24
    "path
    -0.23
    "url
    -0.23
    :Any
    -0.23
    FontAwesomeIcon
    -0.22
    oard
    -0.22
    evity
    -0.22
    icaid
    -0.22
    terior
    -0.22
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.33
    åĴĮåľ°åĮº
    0.31
    /column
    0.24
     of
    0.23
    éĹ´çļĦ
    0.23
    éĥ½æľīèĩªå·±
    0.22
    éĹ´
    0.22
    -wise
    0.21
    /categories
    0.21
    wise
    0.20
    Activations Density 4.687%

    No Known Activations