© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19768
    Prev
    Next
    INDEX
    Explanations

    collaboration, cooperation, together

    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
     اÙĦتابعة
    -0.09
    ieg
    -0.09
    宵
    -0.09
    æľį
    -0.08
    istine
    -0.08
    åIJĪçIJĨçļĦ
    -0.08
    深深çļĦ
    -0.08
    лиÑģÑĮ
    -0.08
    æĨ§
    -0.08
     WATCH
    -0.08
    POSITIVE LOGITS
    é»ĺå¥ij
    0.13
    åħ±å»º
    0.12
    æIJŃæ¡£
    0.11
    äºĮ人
    0.11
    ä¿©
    0.11
    两人
    0.10
    å¼ĢåĬŀ
    0.09
    ä¼Ļä¼´
    0.09
    两个人
    0.09
    äºĴè¡¥
    0.09
    Activations Density 0.076%

    No Known Activations