© 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. 61895
    Prev
    Next
    INDEX
    Explanations

    cleaning and preparing 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
    åĨ¶
    -0.08
    åĵº
    -0.08
    æİ¥è¿ĩ
    -0.08
    ä¹ı
    -0.08
    IEEE
    -0.08
    éħª
    -0.08
    å¤Ń
    -0.08
     Champ
    -0.08
    cran
    -0.08
     Dough
    -0.08
    POSITIVE LOGITS
    å¹²åĩĢ
    0.12
    æ´Ĺå¹²åĩĢ
    0.11
    认æ¸ħ
    0.10
    æĿĤè´¨
    0.10
    æ´ģ
    0.09
    æݾ
    0.09
    æ´ĹåĩĢ
    0.09
    éĢīæĭ
    0.09
    çļĦæľĭåıĭ
    0.09
    rics
    0.09
    Activations Density 0.011%

    No Known Activations