© 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. 6919
    Prev
    Next
    INDEX
    Explanations

    codes and coupons

    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
    cern
    -0.09
    PerPixel
    -0.08
    lesi
    -0.08
    åĢ¡å¯¼
    -0.08
    ãĤ«ãĥĨ
    -0.08
    stell
    -0.08
    arning
    -0.08
    æijĦ
    -0.08
    ibri
    -0.08
     elems
    -0.08
    POSITIVE LOGITS
     coupons
    0.14
     coupon
    0.14
    coupon
    0.13
    åĪ¸
    0.12
     Coupons
    0.12
     Coupon
    0.12
    åĩŃè¯ģ
    0.11
    çºłéĶĻ
    0.11
    _coupon
    0.10
    礼åĵģ
    0.10
    Activations Density 0.063%

    No Known Activations