© 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. 26209
    Prev
    Next
    INDEX
    Explanations

    schools and institutes

    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
    åĶ®åIJİ
    -0.10
    åIJĦè¡Į
    -0.10
    éĽĨåĽ¢èĤ¡ä»½
    -0.09
    çĭ¬ç«ĭèij£äºĭ
    -0.08
    åIJĮå¿ĥ
    -0.08
    çĽijäºĭä¼ļ
    -0.08
    éĨį
    -0.08
     Lac
    -0.08
    æĪijçļĦå¿ĥ
    -0.08
    ãĥĪãĥ©
    -0.08
    POSITIVE LOGITS
    å®ł
    0.09
    ç½ħ
    0.09
    uxt
    0.09
     Controls
    0.08
    è´ŁéĿ¢
    0.08
    éĥ¨
    0.08
    幸
    0.08
    totalCount
    0.08
    announce
    0.08
    voke
    0.08
    Activations Density 0.059%

    No Known Activations