© 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
    2. Qwen2.5-7B-IT
    3. 20-MATRYOSHKA-65K
    4. 789
    Prev
    Next
    INDEX
    Explanations

    foreign text

    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
    estruction
    -0.32
    >NN
    -0.32
    grily
    -0.32
     CircularProgress
    -0.29
    :<?
    -0.28
    西红
    -0.28
    >manual
    -0.27
     hubby
    -0.27
    mbH
    -0.27
    "While
    -0.27
    POSITIVE LOGITS
     erfolgre
    0.31
    idée
    0.30
    çī¹åΫ声æĺİ
    0.28
    ÙĨاÙĤØ´
    0.25
     libertin
    0.23
     hookup
    0.23
    OCKET
    0.23
    ç¢ĺ
    0.23
    RITE
    0.22
     unterstüt
    0.22
    Activations Density 10.636%

    No Known Activations