© 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. 1002
    Prev
    Next
    INDEX
    Explanations

    requirements and functions

    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
    idUser
    -0.42
    à¦Ī
    -0.35
    à¤ĭ
    -0.31
    à¤ij
    -0.31
    à°Ī
    -0.28
    Êķ
    -0.26
    zeÅĦ
    -0.26
    koa
    -0.25
    ʺ
    -0.24
    à®ĵ
    -0.24
    POSITIVE LOGITS
     till
    0.40
     equipments
    0.33
     atleast
    0.31
     novitÃł
    0.31
     automát
    0.30
     Till
    0.30
     upto
    0.29
    )throws
    0.29
     necessitÃł
    0.28
    讵
    0.27
    Activations Density 9.492%

    No Known Activations