© 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. 2667
    Prev
    Next
    INDEX
    Explanations

    recent

    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
    HandlerContext
    -0.24
    eggies
    -0.22
    ustralian
    -0.22
    -Trump
    -0.21
    flix
    -0.21
     fName
    -0.21
    .GetInstance
    -0.20
    ForMember
    -0.20
    bservable
    -0.20
    .GetChild
    -0.19
    POSITIVE LOGITS
    @show
    0.24
    éĶĥ
    0.23
    =YES
    0.23
    çĹĦ
    0.23
    GRAM
    0.23
     acompaña
    0.22
     dumpsters
    0.21
    }elseif
    0.21
    ,},↵
    0.21
    ly
    0.20
    Activations Density 0.202%

    No Known Activations