© 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. 19401
    Prev
    Next
    INDEX
    Explanations

    fundaciones y orquestas

    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
    ä¸ĢçĤ¹åĦ¿
    -0.13
    çĤ¹åĦ¿
    -0.12
    èĩ³æĸ¼
    -0.11
    æĸ¼
    -0.10
    ä¹İ
    -0.10
     López
    -0.09
    çĦ¶æĺ¯
    -0.09
    æĸ¼æĺ¯
    -0.09
    äºĭåĦ¿
    -0.09
     MarÃŃa
    -0.09
    POSITIVE LOGITS
    acute
    0.10
    Ëī
    0.09
    ÃĮ
    0.09
    ¯
    0.09
    ´
    0.08
    说æĺ¯
    0.08
    æ´¼
    0.08
    ÌĢ
    0.08
    rawl
    0.08
     Â
    0.08
    Activations Density 0.211%

    No Known Activations