© 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. 52331
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by technology/proper nouns

    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
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.13
    äºĨä¸įå°ij
    -0.10
    å°¤åħ¶
    -0.10
    /ec
    -0.09
    尤为
    -0.09
    æĹłä¸į
    -0.09
    å¾Īæľīåı¯èĥ½
    -0.09
     pháºŃn
    -0.09
    åIJĦé¡¹å·¥ä½ľ
    -0.09
    æľīä»»ä½ķ
    -0.09
    POSITIVE LOGITS
    åı¦æľī
    0.16
    åı¦å¤ĸ
    0.15
    è¦ģä¹Ī
    0.13
     elsewhere
    0.12
    åı¦è¡Į
    0.12
    åı¦
    0.11
    åł¡
    0.10
    åĪ¥ãģ®
    0.10
    åħ¶ä»ĸ
    0.10
    å¹Į
    0.10
    Activations Density 0.275%

    No Known Activations