© 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. 806
    Prev
    Next
    INDEX
    Explanations

    "-able" or "-ing" endings

    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
     Millenn
    -0.37
    ournemouth
    -0.36
     consect
    -0.32
     Silicone
    -0.29
     Hindered
    -0.29
    theless
    -0.28
    úsqueda
    -0.27
     tph
    -0.25
     Tradable
    -0.25
    ÑĥниÑĨип
    -0.24
    POSITIVE LOGITS
    ning
    0.33
    grily
    0.30
    velope
    0.27
     Ấ
    0.27
    forgettable
    0.26
    thinkable
    0.26
    NING
    0.25
    /OR
    0.25
    precedented
    0.25
    ventario
    0.25
    Activations Density 11.042%

    No Known Activations