© 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. 901
    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
    UGC
    -0.23
    åłį
    -0.21
    çĻĥ
    -0.21
    主ä¹īæĢĿæĥ³
    -0.20
    ServletRequest
    -0.20
    saldo
    -0.20
    çıŃ
    -0.20
    Cadastro
    -0.19
     ESV
    -0.19
    æĬ»
    -0.19
    POSITIVE LOGITS
     lawy
    0.20
     ActionTypes
    0.20
    gar
    0.20
    pedia
    0.20
    duino
    0.20
    rip
    0.19
    izzas
    0.19
    åĹIJ
    0.19
    oh
    0.19
    étude
    0.19
    Activations Density 0.000%

    No Known Activations