© 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. 38983
    Prev
    Next
    INDEX
    Explanations

    make predictions or recommendations

    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
    uur
    -0.10
    è¿Ļ个ä¸ĸçķĮ
    -0.09
     Schro
    -0.09
    åľ¨éĤ£éĩĮ
    -0.09
     errorHandler
    -0.08
    è§IJ
    -0.08
    èµ°åIJij
    -0.08
    vla
    -0.08
    æ£īèĬ±
    -0.08
    溶
    -0.08
    POSITIVE LOGITS
    æĦıè¯ĨåĪ°
    0.10
     aware
    0.09
    pon
    0.09
    çĶŁäº§åĬĽ
    0.09
    ercul
    0.09
    æıIJä¾Ľä¼ĺè´¨
    0.09
    ä¸įæĪIJ
    0.08
    许
    0.08
    é²ľ
    0.08
     Hunting
    0.08
    Activations Density 0.038%

    No Known Activations