© 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. 2397
    Prev
    Next
    INDEX
    Explanations

    measurement analysis

    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
    param
    -0.21
     param
    -0.20
    è½µ
    -0.19
    ëĵ¬
    -0.19
     crossorigin
    -0.19
    ìĤ¿
    -0.18
    èĬ¼
    -0.18
    æªĶ
    -0.18
    éĵ
    -0.18
     HuffPost
    -0.18
    POSITIVE LOGITS
    éħ©
    0.20
    èĵ¼
    0.20
    çĽħ
    0.20
    .LoggerFactory
    0.20
    ç½ijç«Ļé¦ĸ页
    0.19
     ()->
    0.19
    eah
    0.19
     Ventura
    0.19
    .CONNECT
    0.18
     présenté
    0.18
    Activations Density 0.097%

    No Known Activations