© 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. 630
    Prev
    Next
    INDEX
    Explanations

    cognitive development and thinking

    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
    åĵģä½į
    -0.09
    ä¸įå°½
    -0.09
    åĨ³å¿ĥ
    -0.08
    æī©æķ£
    -0.08
    æĶ¾åĩº
    -0.08
    ä¸Ģç§Ĵ
    -0.08
    èĬ¬
    -0.08
    erea
    -0.08
    容
    -0.08
    å°ģ
    -0.08
    POSITIVE LOGITS
    åĦ¿ç«¥
    0.11
    abay
    0.11
    åħĴç«¥
    0.10
    æ¯įå©´
    0.10
     developmental
    0.10
    æ´¾
    0.09
    å©´å¹¼åĦ¿
    0.09
    å¹¼åĦ¿
    0.09
    ç³ķ
    0.09
    _crypto
    0.09
    Activations Density 0.065%

    No Known Activations