© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56154
    Prev
    Next
    INDEX
    Explanations

    past and present forms of 'to have'

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä»Ģä¹Īåij¢
    -0.09
    大è¡Ĺ
    -0.09
    åŀ£
    -0.09
    ãģ°ãģĭãĤĬ
    -0.09
    åIJĥè¿ĩ
    -0.09
    UNT
    -0.09
    exec
    -0.08
    æİ¥åĪ°
    -0.08
    æ¯ģ
    -0.08
    .jp
    -0.08
    POSITIVE LOGITS
    appe
    0.10
    æŃ£å¦Ĥ
    0.09
    å²ĺ
    0.09
    æĦıåĽ¾
    0.09
     legisl
    0.09
    æıIJåĩºçļĦ
    0.08
    æĶ¯éĺŁ
    0.08
    ç¬ijç¬ij
    0.08
    èĤĭ
    0.08
     sez
    0.08
    Activations Density 0.139%

    No Known Activations