© 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. 461
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    استÙĤÙĦ
    -0.23
    .Euler
    -0.22
    arnation
    -0.22
    çŀł
    -0.21
    ("")]↵
    -0.21
    пеÑĩ
    -0.20
     ******************************************************************************/↵
    -0.20
    agma
    -0.19
    .reactivex
    -0.19
     Kurdistan
    -0.19
    POSITIVE LOGITS
     sophistic
    0.26
     enthusi
    0.25
    byss
    0.24
     incompet
    0.23
     therap
    0.23
     bureaucr
    0.23
    enment
    0.23
    	So
    0.22
     jó
    0.22
    ListGroup
    0.22
    Activations Density 0.297%

    No Known Activations