© 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. 19458
    Prev
    Next
    INDEX
    Explanations

    peace and friendship, reconciliation, understanding between groups

    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
    ä»İ严
    -0.11
    çĶŁæ¶¯
    -0.10
    è¿Ļå¥Ĺ
    -0.10
    åIJij社ä¼ļ
    -0.10
    éĢĤåIJĪèĩªå·±
    -0.10
    å·¥åķĨå±Ģ
    -0.10
    æĮĤåı·
    -0.10
    å½ĺ
    -0.09
    æĻ¯å¾·
    -0.09
    è¾°
    -0.09
    POSITIVE LOGITS
    æĸĩåĮĸ交æµģ
    0.13
    å¢ŀè¿Ľ
    0.13
    交æµģ
    0.12
     Fist
    0.11
    å½¼æѤ
    0.11
     mutual
    0.10
    æ²ŁéĢļ
    0.10
    æı¡æīĭ
    0.10
    æ¶ĪéĻ¤
    0.10
    shal
    0.10
    Activations Density 0.063%

    No Known Activations