© 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. 20838
    Prev
    Next
    INDEX
    Explanations

    languages and translation

    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
    etas
    -0.09
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.08
    eway
    -0.08
    ÅĪ
    -0.08
    殿
    -0.08
    éķ¿è¾Ī
    -0.08
    æĸ½èĤ¥
    -0.08
    âĢº
    -0.08
    ä¸įåĬ¨
    -0.08
    arro
    -0.07
    POSITIVE LOGITS
    è¯Ńè¨Ģ
    0.21
    å¤ĸè¯Ń
    0.20
     languages
    0.18
    çļĦè¯Ńè¨Ģ
    0.18
    -language
    0.18
     language
    0.17
    èĭ±è¯Ń
    0.17
    ç¿»è¯ij
    0.17
    èªŀè¨Ģ
    0.16
    æĸ¹è¨Ģ
    0.16
    Activations Density 0.185%

    No Known Activations