© 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. 21429
    Prev
    Next
    INDEX
    Explanations

    Cayce or Cayley

    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
     Bout
    -0.09
    LESS
    -0.09
    Ùĥت
    -0.09
    ç½®æį¢
    -0.08
    åĭĥåĭĥ
    -0.08
    -fw
    -0.08
    incy
    -0.08
    å¼ĵ
    -0.08
    phy
    -0.08
     crowds
    -0.08
    POSITIVE LOGITS
    éļ¾æĢª
    0.10
    culate
    0.10
    å°ijæķ°æ°ijæĹı
    0.09
    OrUpdate
    0.09
    ÙĪاس
    0.09
    èł
    0.09
    aspers
    0.09
    ATAR
    0.08
    åĩĨæŶ
    0.08
    æĪ·
    0.08
    Activations Density 0.030%

    No Known Activations