© 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. 2804
    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
    :".$
    -0.28
    oriously
    -0.24
     Incontri
    -0.24
    '/>
    -0.22
    )(((
    -0.22
    )((((
    -0.22
     ((__
    -0.22
    Direccion
    -0.21
     (){
    -0.21
     deltaY
    -0.21
    POSITIVE LOGITS
    奥巴
    0.21
    éĽģ
    0.21
    SearchTree
    0.20
    è°¡
    0.19
    tridge
    0.19
    atoire
    0.18
    implements
    0.18
     sincere
    0.18
    raf
    0.18
    dbcTemplate
    0.18
    Activations Density 0.000%

    No Known Activations