© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50638
    Prev
    Next
    INDEX
    Explanations

    vacation and holidays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    æ¡£
    -0.09
    ä¸Ģ个个
    -0.08
    æ¼³
    -0.08
    Ñģел
    -0.08
    æĭ©
    -0.08
    çł¥
    -0.08
    bron
    -0.08
    ç¼´è´¹
    -0.08
    ç¿ł
    -0.08
    çĥŃ度
    -0.08
    POSITIVE LOGITS
    ä¼ijåģĩ
    0.15
    holiday
    0.11
    åģĩæľŁ
    0.11
    æ³ķå®ļ
    0.10
    åģĩ
    0.10
    æĶ¾åģĩ
    0.09
     holiday
    0.09
    åħ¨ä½ĵåijĺå·¥
    0.09
     Vacation
    0.09
     Holiday
    0.09
    Activations Density 0.029%

    No Known Activations