© 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. 2208
    Prev
    Next
    INDEX
    Explanations

    programming identifiers

    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
    igne
    -0.23
     stripes
    -0.19
    æķ´çIJĨ
    -0.19
    atype
    -0.19
    ictures
    -0.19
    ëĸ¨
    -0.18
    .Process
    -0.18
    entityManager
    -0.18
    ictim
    -0.18
    åĮłå¿ĥ
    -0.18
    POSITIVE LOGITS
    /Dk
    0.28
     XCT
    0.22
    .databinding
    0.21
     Vance
    0.21
    .yy
    0.21
    ç²Ŀ
    0.21
    .clientY
    0.20
    çĸĸ
    0.20
    getti
    0.20
    =findViewById
    0.20
    Activations Density 0.190%

    No Known Activations