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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9456
    Prev
    Next
    INDEX
    Explanations

    various descriptive phrases

    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
    ONG
    -0.09
    纺ç»ĩ
    -0.09
     ÑģобÑģÑĤвенно
    -0.09
    çļĦæĦıä¹ī
    -0.08
    çŃĶåį·
    -0.08
     kız
    -0.08
    åīª
    -0.08
    åĽ¿
    -0.08
    OUNDS
    -0.08
    åIJĦè¡Į
    -0.08
    POSITIVE LOGITS
    çī¹çĤ¹æĺ¯
    0.09
    ç¡IJ
    0.09
     features
    0.08
    é¢ľåĢ¼
    0.08
    æIJ¦
    0.08
    å¤ĸå½¢
    0.08
    éĢŁåº¦å¿«
    0.08
    -feature
    0.08
    çģµæ´»æĢ§
    0.08
    ä¸ļåĨħ
    0.08
    Activations Density 0.186%

    No Known Activations