© 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. 52860
    Prev
    Next
    INDEX
    Explanations

    make it a

    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
    æİ¢
    -0.09
    å¢ĥ
    -0.09
    à¹īà¸Ńà¸ĩ
    -0.08
    çħ§
    -0.08
    olle
    -0.08
    кÑĥÑģ
    -0.08
    åħĭæĭī
    -0.08
     Airbnb
    -0.08
    Kent
    -0.08
    æĮĤ
    -0.08
    POSITIVE LOGITS
    istically
    0.10
    çªł
    0.10
    åģļçļĦäºĭ
    0.10
    åģļçļĦäºĭæĥħ
    0.09
    æĪIJè´¥
    0.09
    çĦ¶æĺ¯
    0.09
     |_|
    0.09
    èĦı
    0.08
    ä¸Ģå¼ł
    0.08
    èĸ®
    0.08
    Activations Density 0.024%

    No Known Activations