© 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. 62793
    Prev
    Next
    INDEX
    Explanations

    updates

    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¸Ģæī¹
    -0.10
    æĺ§
    -0.09
    same
    -0.09
    ãģ¨åIJĮãģĺ
    -0.09
    ä¸Ģæł·
    -0.08
    lop
    -0.08
    ÑĤан
    -0.08
     same
    -0.08
    Same
    -0.08
    .spark
    -0.08
    POSITIVE LOGITS
    åħ·ä½ĵæĥħåĨµ
    0.14
     upcoming
    0.11
    è¿Ļ次
    0.11
     ÙĪعÙĨ
    0.11
    èĥĮåIJİçļĦ
    0.11
    ä½ľåĵģåĨħ容
    0.11
    æŃ¤æ¬¡æ´»åĬ¨
    0.10
    è¿ĻæĶ¯
    0.10
    è¿Ļ件äºĭ
    0.10
    æĸĩåĮĸåĴĮ
    0.10
    Activations Density 0.273%

    No Known Activations