© 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. 2520
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    enment
    -0.23
    ;]/
    -0.21
    xfb
    -0.20
    ASI
    -0.20
     citiz
    -0.19
    onaut
    -0.19
    .Xr
    -0.19
    ionage
    -0.18
    kelas
    -0.18
    upakan
    -0.18
    POSITIVE LOGITS
    ::<
    0.26
    asInstanceOf
    0.24
    <T
    0.23
    eparator
    0.22
    <int
    0.21
    (()=>
    0.21
    <
    0.21
    \<
    0.20
    æĹ¶ä»£ä¸ŃåĽ½
    0.19
    ĤŃ
    0.19
    Activations Density 0.108%

    No Known Activations