© 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. 52119
    Prev
    Next
    INDEX
    Explanations

    safety and security

    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
    å¥Ĥ
    -0.08
    人次
    -0.08
    ä¸įåĩĨ
    -0.08
    çĢĽ
    -0.08
    ç§Ģ
    -0.08
    å¹²éĥ¨
    -0.08
    磷
    -0.08
     Leg
    -0.07
    å»ĵ
    -0.07
    çħ§æł·
    -0.07
    POSITIVE LOGITS
    ç½ij绾å®īåħ¨
    0.10
     ré
    0.10
    acked
    0.09
    éĩijèŀįåį±æľº
    0.09
    éļIJç§ģ
    0.09
    æ±Łæ¹ĸ
    0.09
    isque
    0.09
    åĮ£
    0.09
    ä¿¡æģ¯å®īåħ¨
    0.09
    ä¼Ļä¼´åħ³ç³»
    0.09
    Activations Density 0.172%

    No Known Activations