© 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. 63973
    Prev
    Next
    INDEX
    Explanations

    TweetDeck, coconut oil, milk, melioidosis

    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
    æ¶ħ
    -0.10
    çŃī级
    -0.09
    éķĬ
    -0.09
    æıIJæĹ©
    -0.09
    æĮŁ
    -0.09
    åı±
    -0.09
    缣
    -0.08
    çīĪ
    -0.08
     Mars
    -0.08
    ê°Ī
    -0.08
    POSITIVE LOGITS
    åħħåĪĨä½ĵçİ°
    0.09
     Rand
    0.09
    é¢Ģ
    0.09
    æµĵæµĵçļĦ
    0.09
     pens
    0.09
    翳
    0.08
    æīĵæĸŃ
    0.08
    æ»ļæ»ļ
    0.08
    umping
    0.08
    èĩ¾
    0.08
    Activations Density 0.001%

    No Known Activations