© 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. 1331
    Prev
    Next
    INDEX
    Explanations

    code

    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
    "
    -0.25
     pó
    -0.23
     ëĮĢíķ´ìĦľ
    -0.21
    olynomial
    -0.20
     chá
    -0.20
    “
    -0.20
    lsx
    -0.20
    ppelin
    -0.19
    -long
    -0.19
    etCode
    -0.19
    POSITIVE LOGITS
     createState
    0.30
    :".$
    0.29
    ;base
    0.27
    :<?
    0.27
    ',//
    0.27
    :;↵
    0.27
    ";//
    0.27
    <path
    0.26
    /↵↵↵↵
    0.26
    对åħ¶çľŁå®ŀ
    0.26
    Activations Density 1.558%

    No Known Activations