© 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. 51291
    Prev
    Next
    INDEX
    Explanations

    date stamp time

    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
    çī¹è´¨
    -0.10
     Heritage
    -0.10
    ä¸Ģåı·
    -0.09
    зÑĭ
    -0.09
    intree
    -0.09
     пÑĢоб
    -0.09
    лиÑĨ
    -0.09
    ãĥķãĤ¡ãĥ¼
    -0.09
    ·»
    -0.08
    å¼Ģåı£
    -0.08
    POSITIVE LOGITS
    æĹ¥æľŁ
    0.16
     date
    0.16
    stamp
    0.14
    date
    0.14
     Date
    0.13
     stamp
    0.13
    Date
    0.12
    .getDate
    0.12
    -date
    0.12
     DATE
    0.11
    Activations Density 0.141%

    No Known Activations