© 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. 61873
    Prev
    Next
    INDEX
    Explanations

    real estate company or firm

    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
    çľ¼åīįçļĦ
    -0.10
    çľ¼åīį
    -0.09
    åĵī
    -0.09
    idia
    -0.09
    æĺ¯ä¸Ģ项
    -0.09
    è¿Ļæīįæĺ¯
    -0.09
    èµ·æĿ¥äºĨ
    -0.09
    è¿ĻäºĽä¸ľè¥¿
    -0.09
    éĹ®ä»ĸ
    -0.09
    ennes
    -0.09
    POSITIVE LOGITS
    æĽ¾
    0.10
    åIJĮæĹ¶ä¹Łæĺ¯
    0.09
    èĤļåŃIJ
    0.09
    对该
    0.09
     excell
    0.09
    åīį身
    0.09
    OrNull
    0.08
     whose
    0.08
    æĺ¨
    0.08
    çķ´
    0.08
    Activations Density 0.299%

    No Known Activations