© 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. 63523
    Prev
    Next
    INDEX
    Explanations

    day or holiday celebration

    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
    rowned
    -0.10
    åĶ®ä»·
    -0.10
    éĮ¾
    -0.09
    SSIP
    -0.09
    å®ļå±ħ
    -0.09
    è·¯æ¼Ķ
    -0.09
    讲课
    -0.08
    prefs
    -0.08
     alm
    -0.08
    Ñĥнк
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸Ģ天
    0.14
    èĬĤæĹ¥
    0.13
    é£İä¿Ĺ
    0.12
    ä¹łä¿Ĺ
    0.12
    æ¯ıå¹´
    0.12
    ä¸Ģå¹´ä¸Ģ度
    0.11
    æĦıä¹ī
    0.11
    åį³å°ĨåĪ°æĿ¥
    0.11
    为ä»Ģä¹Īè¦ģ
    0.10
    æĶ¾åģĩ
    0.10
    Activations Density 0.121%

    No Known Activations