© 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. 10520
    Prev
    Next
    INDEX
    Explanations

    languages, linguistic 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
    精彩
    -0.10
    åħ¬åĬŀ
    -0.10
    ç²¾
    -0.10
    ÙĨÙĬÙĨ
    -0.10
    导åIJij
    -0.09
    寺
    -0.09
    京åŁİ
    -0.09
    æŀľ
    -0.09
    çĶ¨çĶµ
    -0.09
    alık
    -0.08
    POSITIVE LOGITS
    å¤ļå°ij
    0.09
    ç³»
    0.09
    éģĹçķĻ
    0.09
     Homeland
    0.09
    èĢ¨
    0.08
    emed
    0.08
    è¯Ńè¨Ģ
    0.08
    æľ¬è´¨ä¸Ĭ
    0.08
     languages
    0.08
    prox
    0.08
    Activations Density 0.131%

    No Known Activations