© 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. 29466
    Prev
    Next
    INDEX
    Explanations

    news from

    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
    uer
    -0.09
    ä¸įè¡Į
    -0.09
    å¤ļ次
    -0.09
     Charg
    -0.09
    har
    -0.08
    åij¨æľ«
    -0.08
    åĩłæ¬¡
    -0.08
    ãģŁãģı
    -0.08
    讫
    -0.08
    产çĶŁäºĨ
    -0.08
    POSITIVE LOGITS
    çĤ¹äºĨ
    0.10
    身éĤĬ
    0.09
    ’T
    0.09
    ’B
    0.09
    纳
    0.09
    豪
    0.09
    åĴĮåıijå±ķ
    0.09
    ê¹ĥ
    0.09
    身边çļĦ
    0.09
    缴è¾ĸ
    0.08
    Activations Density 0.016%

    No Known Activations