© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 27
    Prev
    Next
    INDEX
    Explanations

    ency

    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
    o
    -0.27
    i
    -0.26
    er
    -0.22
     tablename
    -0.20
     sqlCommand
    -0.20
    en
    -0.19
    al
    -0.19
    z
    -0.19
    u
    -0.19
    over
    -0.19
    POSITIVE LOGITS
    @dynamic
    0.32
    gnore
    0.28
     misunder
    0.27
    çļĦ带é¢Ĩ
    0.27
    :"-
    0.27
    /Dk
    0.27
     embod
    0.25
    phia
    0.25
    :System
    0.25
    "display
    0.24
    Activations Density 10.918%

    No Known Activations