© 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. 7548
    Prev
    Next
    INDEX
    Explanations

    of [Place Name]

    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
    æŶæŶ
    -0.09
    å¤Ļ
    -0.08
    è¾Ł
    -0.08
    èĹķ
    -0.08
     own
    -0.08
    own
    -0.08
     conversion
    -0.08
    овиÑĩ
    -0.08
    converted
    -0.08
    æīįèĥ½
    -0.08
    POSITIVE LOGITS
    纶
    0.11
    ä¸ŃåĽ½çļĦ
    0.11
    åĮĹæĸĹ
    0.09
    errs
    0.09
    èĥĮéĥ¨
    0.09
    otify
    0.09
    主æĿ¿
    0.08
    ilik
    0.08
    å¼¹
    0.08
    å¤ļç§įå½¢å¼ı
    0.08
    Activations Density 0.095%

    No Known Activations