© 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. 36124
    Prev
    Next
    INDEX
    Explanations

    New York court cases

    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
    让æĤ¨
    -0.10
    éħįçĶµ
    -0.09
    å¾Īæľī
    -0.08
    ãģ«å¯
    -0.08
    crud
    -0.08
    çľĭå¾Ĺ
    -0.08
    å¼¹
    -0.08
    CS
    -0.08
    .sw
    -0.08
    æµ·æ°´
    -0.08
    POSITIVE LOGITS
    æ±°
    0.11
     اÙĦÙħÙĩ
    0.10
    èIJ½ä¸ĭ
    0.10
    éĶ»
    0.10
    åĬ³
    0.09
    елÑĮ
    0.09
    äºķ
    0.09
     гÑĢаÑĦик
    0.09
    cka
    0.09
    berger
    0.09
    Activations Density 0.234%

    No Known Activations