© 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. 55477
    Prev
    Next
    INDEX
    Explanations

    very, still, was, 'm, love

    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
    è¾¾æłĩ
    -0.10
    以åħį
    -0.10
    æľĢ为
    -0.10
    ãģĵãĤĮãĤī
    -0.10
    æŀģ为
    -0.10
    é¢ĩ为
    -0.10
    æĹłè®ºå¦Ĥä½ķ
    -0.10
    æı¡æīĭ
    -0.09
    è¿Ļæł·åģļ
    -0.09
    æĺ¯éĿŀ常
    -0.09
    POSITIVE LOGITS
    å°¤åħ¶æĺ¯åľ¨
    0.09
    icate
    0.09
     especially
    0.09
    ä½Ĩä¹Ł
    0.09
    7
    0.08
    å°¤åħ¶
    0.08
    æľīæľºä¼ļ
    0.08
    çī¹åĪ«æĺ¯åľ¨
    0.07
     Moor
    0.07
    以åīį
    0.07
    Activations Density 0.151%

    No Known Activations