© 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. 29477
    Prev
    Next
    INDEX
    Explanations

    dates and times in text

    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
    èĦĶ
    -0.10
    å°ıæŶåīį
    -0.09
    èĢģ人家
    -0.09
    leave
    -0.09
    顶端
    -0.09
    奥è¿IJä¼ļ
    -0.09
    è´§æŀ¶
    -0.09
    æĪijèĩªå·±
    -0.09
    Ticker
    -0.09
    åĩłå¹´åīį
    -0.09
    POSITIVE LOGITS
     pret
    0.09
    è¹²
    0.09
     tact
    0.09
    çıĪ
    0.08
    å¤ļå±Ĥ次
    0.08
    åīįä¸ī
    0.08
    åį³
    0.08
    ferred
    0.08
    ’ll
    0.08
    -location
    0.08
    Activations Density 0.064%

    No Known Activations