© 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. 29653
    Prev
    Next
    INDEX
    Explanations

    version or edition information

    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
    èµ°ä¸ĭåİ»
    -0.09
    æ´ĩ
    -0.09
    License
    -0.08
    踯
    -0.08
    ç»ĵæŀĦè°ĥæķ´
    -0.08
    å¢ĥ
    -0.08
    çīĮçħ§
    -0.08
    èµĦ讯
    -0.08
    èĹı
    -0.08
    bst
    -0.08
    POSITIVE LOGITS
    çīĪæľ¬
    0.32
     version
    0.30
     versions
    0.25
    çīĪ
    0.25
     versión
    0.25
    version
    0.23
     Version
    0.21
    .version
    0.20
    _version
    0.20
    	version
    0.20
    Activations Density 0.224%

    No Known Activations