© 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. 2354
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    å¼Ģå¥ĸç»ĵæŀľ
    -0.25
    袱
    -0.23
    DSP
    -0.21
     cref
    -0.21
    ãİĿ
    -0.20
     CDDL
    -0.20
    çºŃ
    -0.20
     pione
    -0.20
     MPU
    -0.19
    dio
    -0.19
    POSITIVE LOGITS
    .createStatement
    0.22
    ften
    0.20
    (pow
    0.20
    åĵĢ
    0.20
     und
    0.19
    uzzer
    0.19
    comed
    0.19
    .joda
    0.19
    =\"#
    0.19
    oftware
    0.19
    Activations Density 0.001%

    No Known Activations