© 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. 1957
    Prev
    Next
    INDEX
    Explanations

    derivative

    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
    exampleModal
    -0.24
     CONTR
    -0.21
    )init
    -0.21
     malaysia
    -0.21
    myModal
    -0.20
    overe
    -0.20
    çħĬ
    -0.20
     proport
    -0.19
     Fallon
    -0.19
     reuseIdentifier
    -0.19
    POSITIVE LOGITS
    âĦħ
    0.24
    mouseleave
    0.24
    bserv
    0.23
    ivative
    0.23
    ðŁ¥ĩ
    0.21
     derivative
    0.20
    è°Ķ
    0.20
    "sync
    0.20
    Serviço
    0.20
    ürger
    0.20
    Activations Density 0.339%

    No Known Activations