© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3940
    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
    ABCDEFGHIJKLMNOP
    -0.24
     HuffPost
    -0.22
     Chore
    -0.22
     }}>{
    -0.21
     miÄĻdz
    -0.21
     __________________↵↵
    -0.21
     Playoff
    -0.21
     )↵↵↵↵↵↵↵↵
    -0.21
     Ä°stanbul
    -0.21
    entifier
    -0.21
    POSITIVE LOGITS
     loadChildren
    0.20
     UIScreen
    0.19
    .BLL
    0.19
    ris
    0.19
     testCase
    0.18
    prec
    0.18
    ä¸įå®ī
    0.18
    RunWith
    0.18
    aviours
    0.18
    ",&
    0.17
    Activations Density 0.001%

    No Known Activations