© 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. 51568
    Prev
    Next
    INDEX
    Explanations

    bridge or bridges

    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
    ugs
    -0.09
    åĨħéĥ¨æݧåĪ¶
    -0.08
    æī°
    -0.08
    满èĦ¸
    -0.08
    éĢģæĿ¥
    -0.08
    éºĵ
    -0.08
    ç¼ĩ
    -0.08
    Cons
    -0.08
    è¡ĮæĺŁ
    -0.08
    é¬ĥ
    -0.08
    POSITIVE LOGITS
    æ¡¥æ¢ģ
    0.19
    大桥
    0.17
     bridge
    0.15
     bridges
    0.15
    æ¡¥
    0.15
    .bridge
    0.15
    æ©ĭ
    0.14
     Bridge
    0.13
    bridge
    0.13
     Bridges
    0.12
    Activations Density 0.101%

    No Known Activations