© 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. 51170
    Prev
    Next
    INDEX
    Explanations

    useful descriptors

    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
    ä¸įæĺİçĻ½
    -0.09
    çĵ¢
    -0.08
    ê¶Į
    -0.08
    æĬķèµĦé¢Ŀ
    -0.08
    ç®Ģ
    -0.08
    æī£
    -0.08
    æ¹®
    -0.07
    essel
    -0.07
    绣
    -0.07
    itag
    -0.07
    POSITIVE LOGITS
     useful
    0.19
    æľīçĶ¨çļĦ
    0.17
     usefulness
    0.17
    æľīçĶ¨
    0.17
     Useful
    0.15
     handy
    0.15
     helpful
    0.14
     hữu
    0.14
     Helpful
    0.13
    à¸Ľà¸£à¸°à¹Ĥยà¸Ĭà¸Ļ
    0.13
    Activations Density 0.073%

    No Known Activations