© 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. 16535
    Prev
    Next
    INDEX
    Explanations

    built in or at

    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
    åĵģåij³
    -0.09
    ä¸Ģç±»
    -0.09
    å¿į
    -0.09
    å±ħä½ı
    -0.09
    åĮ¡
    -0.08
    krit
    -0.08
     bumps
    -0.08
    reso
    -0.08
    æ¸ħæĸ°
    -0.08
    çĵ¶
    -0.08
    POSITIVE LOGITS
    åĪ¶éĢł
    0.18
    éĢłèĪ¹
    0.16
    åİĤ
    0.15
     manufacture
    0.15
    åĪ¶éĢłä¸ļ
    0.14
    åĪ¶éĢłåķĨ
    0.14
     factories
    0.14
     manufacturing
    0.14
    製
    0.14
    å»ł
    0.13
    Activations Density 0.135%

    No Known Activations