© 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. 1666
    Prev
    Next
    INDEX
    Explanations

    patent numbers

    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
    CKER
    -0.22
     pione
    -0.22
     councillor
    -0.22
    çļĦ带é¢Ĩ
    -0.21
     ohio
    -0.21
     ThÆ°
    -0.20
     smarty
    -0.20
     célib
    -0.20
    çķĻè¨ĢæĿ¿
    -0.20
     Erot
    -0.20
    POSITIVE LOGITS
    (Have
    0.26
    ouncy
    0.23
    ingly
    0.23
     disastr
    0.21
    EATURE
    0.20
    rog
    0.20
    /Dk
    0.20
    itchens
    0.20
     UClass
    0.20
     سبØŃ
    0.19
    Activations Density 0.942%

    No Known Activations