© 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. 16752
    Prev
    Next
    INDEX
    Explanations

    responsibility for

    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
    对çħ§
    -0.09
    terra
    -0.09
    ç¡®
    -0.08
     Sporting
    -0.08
    麻
    -0.08
    artner
    -0.08
    arma
    -0.08
    маÑĢ
    -0.08
    led
    -0.08
    ç»Ĩç»Ĩ
    -0.08
    POSITIVE LOGITS
    交ç»Ļ
    0.13
    éĩįä»»
    0.11
    åĿĩçĶ±
    0.11
    çīĪæĿĥå½Ĵ
    0.11
    çļĦ责任
    0.11
     bat
    0.10
     responsibility
    0.10
    主ä½ĵ责任
    0.10
    å¼¼
    0.10
    责任æĦŁ
    0.09
    Activations Density 0.088%

    No Known Activations