© 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. 47974
    Prev
    Next
    INDEX
    Explanations

    time, challenges, advantages, data

    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
    æĢĿãģĦ
    -0.09
    ogh
    -0.09
    ilot
    -0.08
    à¸Ńร
    -0.08
    缺å°ij
    -0.08
    .getDouble
    -0.08
    楼主
    -0.08
     Scrolls
    -0.08
    æĮģæľī
    -0.08
     تÙĤ
    -0.08
    POSITIVE LOGITS
    çĦī
    0.11
    çļĦä¸ĢéĿ¢
    0.10
    æľĢå¤ļçļĦ
    0.09
    åIJĦå¼Ĥ
    0.09
    çĶļèĩ³
    0.09
    ereal
    0.08
    å¯¹æľªæĿ¥
    0.08
    ä¸Ģå®ļçļĦ
    0.08
    ä¸į让
    0.08
    å¾Īæĸ¹ä¾¿
    0.08
    Activations Density 0.298%

    No Known Activations