© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26150
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun + time period

    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
    Negative Logits
    ViewItem
    -0.10
    locals
    -0.08
    该项
    -0.08
    客
    -0.08
    亲
    -0.08
    å¸ĤæķĻèĤ²å±Ģ
    -0.08
    æ©ĺ
    -0.08
    ãĤ¹ãĥĶ
    -0.08
    æĤłæĤł
    -0.08
    gars
    -0.07
    POSITIVE LOGITS
    æĹ¶ä»£çļĦ
    0.28
    æĹ¶ä»£
    0.28
    æĻĤ代
    0.25
    è¿Ļ个æĹ¶ä»£
    0.23
    çļĦæĹ¶ä»£
    0.21
    年代
    0.20
     era
    0.18
    æĹ¶ä»£ä¸ŃåĽ½
    0.18
    æĸ°æĹ¶ä»£
    0.16
    -era
    0.14
    Activations Density 0.040%

    No Known Activations