© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4052
    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
    缶
    -0.28
    irlines
    -0.22
     lucr
    -0.21
    æī©
    -0.21
     {!!
    -0.20
     PhpStorm
    -0.20
    MeasureSpec
    -0.20
    åĿĮ
    -0.20
    Ø£ÙĪض
    -0.19
    uckland
    -0.19
    POSITIVE LOGITS
    :animated
    0.26
    iteDatabase
    0.24
    :');↵
    0.24
    emean
    0.21
    :".$
    0.20
    :Any
    0.20
    );$
    0.20
    -muted
    0.20
    chantment
    0.19
    ScrollIndicator
    0.19
    Activations Density 0.001%

    No Known Activations