© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34978
    Prev
    Next
    INDEX
    Explanations

    polypropylene, high density, quality, natural, fine china, pine

    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
    ä¾¿å®ľ
    -0.09
    inia
    -0.09
    å¾Īæĸ¹ä¾¿
    -0.08
    糧
    -0.08
    éŀ
    -0.08
    人æīįéĺŁä¼į
    -0.08
    ÐĶаÑĤа
    -0.08
    便
    -0.08
    ullah
    -0.08
    å°Ĩ士
    -0.08
    POSITIVE LOGITS
    æ¢ĵ
    0.09
    éĥĬ
    0.09
    ä¸ĭæīĭ
    0.09
     أج
    0.09
    èī¯å¿ĥ
    0.09
    æĤ¬
    0.08
    ç²¾å¿ĥ
    0.08
     puck
    0.08
    éĢ¼
    0.08
     Forced
    0.08
    Activations Density 0.113%

    No Known Activations