© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50818
    Prev
    Next
    INDEX
    Explanations

    do our best

    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
    å¯Ĵ
    -0.09
     ÙĪÙĦ
    -0.09
    è¦ģåģļåĪ°
    -0.09
    ä¸įäºĨ
    -0.09
    ingu
    -0.09
    æĸ§
    -0.08
    åŃľ
    -0.08
    æľīå¤ļ大
    -0.08
    ำ
    -0.08
    ä½łæĥ³
    -0.08
    POSITIVE LOGITS
    caught
    0.08
    éĴĵ
    0.08
    认è¯Ĩ
    0.08
    åŁºæľ¬æĥħåĨµ
    0.08
    quis
    0.08
    主åĬŀ
    0.08
    è¶ķ
    0.08
    ä¸Ńä»ĭæľºæŀĦ
    0.08
    á»ĩu
    0.07
    类产åĵģ
    0.07
    Activations Density 0.004%

    No Known Activations