© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2955
    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
    èĴ´
    -0.27
     tatto
    -0.23
    itia
    -0.21
     TMZ
    -0.21
     azt
    -0.21
    æijŃ
    -0.20
    busters
    -0.20
    æĸ°æµªè´¢ç»ı
    -0.20
    ancybox
    -0.20
    são
    -0.20
    POSITIVE LOGITS
    ornment
    0.27
    )((((
    0.25
    )(((
    0.23
    çĭĪ
    0.22
    UMB
    0.22
    rip
    0.22
    IndexChanged
    0.21
    InSection
    0.19
    {return
    0.19
    Ĥ¨
    0.19
    Activations Density 0.001%

    No Known Activations