© 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. 288
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specific terms

    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
    åķ¼
    -0.24
    ,retain
    -0.20
     nigeria
    -0.20
     Ä°zmir
    -0.20
     BigInt
    -0.20
    bellion
    -0.20
     Unidos
    -0.19
     promin
    -0.19
     @{↵
    -0.19
     Moff
    -0.19
    POSITIVE LOGITS
    ãİŀ
    0.25
    (strpos
    0.23
    /Register
    0.21
    'icon
    0.21
    èĥ¯
    0.21
    roys
    0.20
    .WindowManager
    0.20
    MMdd
    0.20
    æĢĥ
    0.20
    ï¼ł
    0.19
    Activations Density 0.002%

    No Known Activations