© 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. 57913
    Prev
    Next
    INDEX
    Explanations

    academic work and presentations

    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
    让æ¶Īè´¹èĢħ
    -0.09
    åIJĪèµĦ
    -0.09
    大èĩªçĦ¶
    -0.08
    貫
    -0.08
    acades
    -0.08
    ç«Ł
    -0.08
    æĮĽ
    -0.08
    å½»
    -0.08
    ä¸Ģ大åłĨ
    -0.08
    å·¥ç¨ĭå¸Ī
    -0.08
    POSITIVE LOGITS
    社ç§ij
    0.11
    è¯Ŀè¯Ń
    0.11
    çĶ°éĩİ
    0.11
     Jacket
    0.11
     freshly
    0.09
    çłĶ究ä¸Ńå¿ĥ
    0.09
     Mellon
    0.09
     scholars
    0.09
    å·¥ä½ľç«Ļ
    0.09
    å¼Ģ设
    0.09
    Activations Density 0.162%

    No Known Activations