© 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. 9000
    Prev
    Next
    INDEX
    Explanations

    search results and finding information

    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
    对æłĩ
    -0.11
    路桥
    -0.09
    ä½ĵç³»
    -0.09
    маÑĢк
    -0.09
    ä¸ĢæĶ¯
    -0.09
     Flynn
    -0.09
    çĶŁäº§æĢ»
    -0.09
    ç»Ń
    -0.09
    ÑĤика
    -0.09
    è¿ĻäºĽä¸ľè¥¿
    -0.08
    POSITIVE LOGITS
    æī¾åĪ°
    0.11
    æī¾åĪ°äºĨ
    0.10
     search
    0.09
    /results
    0.09
    æIJľç´¢
    0.09
     results
    0.09
    åħ³èģĶ
    0.08
    æ¶Įçİ°
    0.08
     inhabited
    0.08
    ç»ĵæŀľ
    0.08
    Activations Density 0.200%

    No Known Activations