© 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. 2675
    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
    TouchUpInside
    -0.21
    åŀ¸
    -0.20
     Barg
    -0.19
    koneksi
    -0.19
    èµ·
    -0.19
    ç´łæĻ´
    -0.18
     démarch
    -0.18
     airstrikes
    -0.18
     mutableListOf
    -0.17
    -linear
    -0.17
    POSITIVE LOGITS
    erator
    0.24
    <data
    0.23
    DMETHOD
    0.23
     volunte
    0.23
     fkk
    0.23
    ->[
    0.23
     (!((
    0.22
    .BASELINE
    0.22
    }/#{
    0.22
    -Methods
    0.22
    Activations Density 0.000%

    No Known Activations