© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1929
    Prev
    Next
    INDEX
    Explanations

    date and time formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     suppl
    -0.26
    .Produ
    -0.23
    âĢ¢↵↵
    -0.23
    Injected
    -0.22
    YW
    -0.22
    ÅĪ
    -0.22
     ÐIJлекÑģан
    -0.22
    .Num
    -0.22
    CompanyId
    -0.21
    .BorderColor
    -0.21
    POSITIVE LOGITS
    æł¼å¼ı
    0.30
     format
    0.26
     YYYY
    0.26
     FORMAT
    0.25
    ,date
    0.25
    /calendar
    0.25
     fromDate
    0.24
    -date
    0.23
    format
    0.23
     Date
    0.23
    Activations Density 0.158%

    No Known Activations