© 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. 36262
    Prev
    Next
    INDEX
    Explanations

    will/would followed by a verb

    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
    èĩªèIJ¥
    -0.10
    imedia
    -0.09
    สà¹Ģà¸ķ
    -0.09
     налиÑĩ
    -0.09
    æĶĴ
    -0.09
    STER
    -0.09
    oge
    -0.09
    æī¾åĪ°äºĨ
    -0.09
    è°ĥçłĶ
    -0.08
    æŀģ端
    -0.08
    POSITIVE LOGITS
    å½¼
    0.10
    åıįæĺłåĩº
    0.09
    hu
    0.09
     NOTICE
    0.08
    èĤĮ
    0.08
    åıįæĺł
    0.08
    á»IJ
    0.08
    baugh
    0.08
    éĺ²æŃ¢
    0.08
    éģŃåĪ°
    0.08
    Activations Density 0.055%

    No Known Activations