© 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. 56383
    Prev
    Next
    INDEX
    Explanations

    art museum, college, or institutions

    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
    èµĦæł¼
    -0.13
    овиÑĩ
    -0.11
    ench
    -0.10
    APO
    -0.10
    å¼ıçļĦ
    -0.10
    çĽ
    -0.09
    æĶĢ
    -0.09
    ä¸ĭæīĭ
    -0.09
    ature
    -0.09
    ingly
    -0.09
    POSITIVE LOGITS
    åĪ¤å®ļ
    0.09
    åIJį家
    0.09
    åĽ¢
    0.09
    æ´¥
    0.08
    人士
    0.08
    ONO
    0.08
    çķĮçļĦ
    0.08
    vard
    0.08
     department
    0.08
     Lotto
    0.07
    Activations Density 0.014%

    No Known Activations