© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16730
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun/proper noun

    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
    Negative Logits
    ä¹ŀ
    -0.10
    åįĩé«ĺ
    -0.10
    æī¯
    -0.09
    æĭ´
    -0.09
    æīĵå·¥
    -0.09
    èĪį
    -0.08
    æī§çĿĢ
    -0.08
    çĽĽå®´
    -0.08
    çłį
    -0.08
     Brexit
    -0.08
    POSITIVE LOGITS
    æĬ¥ç¤¾
    0.10
    ç»Łè®¡å±Ģ
    0.09
    ploy
    0.09
    åķĨä¼ļ
    0.09
    ä¿ĿéĻ©åħ¬åı¸
    0.09
     pul
    0.09
    è¿Ļ家åħ¬åı¸
    0.09
    æĹħè¡Į社
    0.08
    è¿Ļ家
    0.08
    ije
    0.08
    Activations Density 0.035%

    No Known Activations