© 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. 740
    Prev
    Next
    INDEX
    Explanations

    organization or news

    np_max-act-logits · gemini-2.5-flash-lite
    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
     ['./
    -0.22
     TMPro
    -0.20
    patch
    -0.20
     bénéficie
    -0.20
     `}↵
    -0.19
     fName
    -0.19
     Alamofire
    -0.19
    جرائÙħ
    -0.18
    chedulers
    -0.18
    åł´åIJĪãģ«ãģ¯
    -0.18
    POSITIVE LOGITS
    #ab
    0.23
    pson
    0.23
    /GPL
    0.22
    ornment
    0.22
    .OrderByDescending
    0.21
    ¡´
    0.21
    ~-~-
    0.20
     поÑĩем
    0.20
    iffany
    0.19
    .IsNullOr
    0.19
    Activations Density 0.001%

    No Known Activations