© 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. 9191
    Prev
    Next
    INDEX
    Explanations

    after me

    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
    æĦ£
    -0.10
    åķ»
    -0.10
    çĵ®
    -0.10
    åĺĽ
    -0.09
    æĿĥçĽĬ
    -0.09
    æĻ¯è±¡
    -0.09
    åIJį声
    -0.09
     Ùħج
    -0.09
    æĹ¶ä»£ä¸ŃåĽ½
    -0.09
    åĵ¨
    -0.09
    POSITIVE LOGITS
     Apr
    0.09
    ä¸įåħĭ
    0.09
    æ¡Ĥ
    0.09
    åIJĦ项
    0.09
    oll
    0.08
    _aw
    0.08
    çļĦåIJĦ项
    0.08
    ullets
    0.08
    Matcher
    0.08
    æĽ´å¤ļçļĦæĺ¯
    0.08
    Activations Density 0.232%

    No Known Activations