© 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. 37219
    Prev
    Next
    INDEX
    Explanations

    written by

    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
    è¿Ļå¥Ĺ
    -0.09
    æŀī
    -0.08
    åĨįå¤ļ
    -0.08
    æīĵ交éģĵ
    -0.08
    ä¸ĭéĿ¢æĺ¯
    -0.08
    å½¢æĪIJçļĦ
    -0.08
    åľ¨ä»ĸ
    -0.08
    èĩ³æѤ
    -0.08
    çĶ·
    -0.08
    upy
    -0.08
    POSITIVE LOGITS
    带åĽŀ
    0.10
    ä½Ĩä¸įéĻIJ
    0.09
    åħ¼
    0.09
    æĶĢçĻ»
    0.09
    çĤ¯
    0.08
    -sdk
    0.08
    è¹²
    0.08
    ä»Ģä¹Īåij¢
    0.08
    uzzi
    0.08
    æĪijçľĭ
    0.08
    Activations Density 0.083%

    No Known Activations