© 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. 6103
    Prev
    Next
    INDEX
    Explanations

    ability to

    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
    رة
    -0.10
    éĿ¢åŃIJ
    -0.09
    æĹĹå¸ľ
    -0.09
    çļĦåĬªåĬĽ
    -0.09
    åİ»äºĨ
    -0.09
    aque
    -0.08
    éĤ£åıª
    -0.08
    ä½ĵçİ°äºĨ
    -0.08
    äºĶä¸Ģ
    -0.08
    è¿ĩäºĨ
    -0.08
    POSITIVE LOGITS
    æĢ§åĴĮ
    0.09
    èĪĽ
    0.09
    å½ĵåľº
    0.09
     both
    0.09
    lé
    0.08
     HOR
    0.08
    å½ĵä¹ĭ
    0.08
    ality
    0.08
    ми
    0.08
    icut
    0.08
    Activations Density 0.050%

    No Known Activations