© 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. 869
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    atu
    -0.21
     repeated
    -0.20
    @protocol
    -0.19
    eneg
    -0.19
     end
    -0.18
    efs
    -0.18
    undi
    -0.18
     chù
    -0.18
    з
    -0.18
    styl
    -0.18
    POSITIVE LOGITS
    íĶĦë¡ľê·¸
    0.24
    kits
    0.22
    STONE
    0.22
    byss
    0.20
     "'.$
    0.20
    è®®äºĭ
    0.19
     assh
    0.19
    Luck
    0.19
    istringstream
    0.19
     Playoff
    0.19
    Activations Density 0.000%

    No Known Activations