© 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. 37019
    Prev
    Next
    INDEX
    Explanations

    dates and timestamps

    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
    éļĶ
    -0.10
    PropertyParams
    -0.09
    ç»´
    -0.09
    è¶ĬæĿ¥
    -0.09
    å¾Ĵ
    -0.09
    EMA
    -0.08
    åį¯
    -0.08
     án
    -0.08
    éĢIJå¹´
    -0.08
    ever
    -0.08
    POSITIVE LOGITS
    æĭĵ宽
    0.09
    åħļçļĦ建设
    0.09
    åħļå»ºå·¥ä½ľ
    0.09
    åıijçĶŁçļĦ
    0.09
    çļĦéĤ£ç§į
    0.09
    -
    0.08
    æĸĩ娱
    0.08
    ä¸įæİĴéĻ¤
    0.08
    ãģ«ãģĬ
    0.08
    è¦ģä¸įçĦ¶
    0.08
    Activations Density 0.044%

    No Known Activations