© 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. 21203
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    æĹ¶ä»£ä¸ŃåĽ½
    -0.11
     Ñģобой
    -0.10
    æĪijåĽ½
    -0.10
    неÑģ
    -0.10
    æķijåij½
    -0.09
    åij¨åĽ´
    -0.09
    ä¹ĭåĬ¿
    -0.09
    æĹ¶ä»£çļĦ
    -0.09
    æĪijçľģ
    -0.08
    æľ¬èº«å°±æĺ¯
    -0.08
    POSITIVE LOGITS
    ä¸İä¸ŃåĽ½
    0.13
    åħ¬å¼ĢèµĽ
    0.11
    个åŁİå¸Ĥ
    0.10
    å¯ĵ
    0.09
    uis
    0.09
    AGED
    0.09
    庶
    0.09
    大åŁİå¸Ĥ
    0.09
    icans
    0.09
    ç§ĥ
    0.09
    Activations Density 0.535%

    No Known Activations