© 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. 2857
    Prev
    Next
    INDEX
    Explanations

    expensive items

    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
    æ»ļæ»ļ
    -0.10
    horn
    -0.09
    èĩªçĦ¶ä¿ĿæĬ¤
    -0.09
    htt
    -0.09
    éľĢæ±Ĥ
    -0.09
    è·Ŀ离
    -0.09
    æĿŀ
    -0.09
    ë¡Ŀ
    -0.08
    å®Īä½ı
    -0.08
    ocha
    -0.08
    POSITIVE LOGITS
    æĺĤè´µ
    0.16
    è´µ
    0.14
     expensive
    0.13
    è²´
    0.12
    é«ĺä»·
    0.12
    à¹ģà¸ŀà¸ĩ
    0.12
    身价
    0.11
     costly
    0.11
    é«ĺæĺĤ
    0.09
    究
    0.09
    Activations Density 0.045%

    No Known Activations