© 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. 54739
    Prev
    Next
    INDEX
    Explanations

    so followed by "why", "what", "once"

    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
    å°¤åħ¶æĺ¯
    -0.12
    çī¹åĪ«æĺ¯
    -0.11
    è¿ĺ好
    -0.11
    åĪļ好
    -0.11
    姻
    -0.11
    æ±°
    -0.10
    ãģĹãģĭãĤĤ
    -0.10
    æĪĸèĢħ说
    -0.10
    ãģĿãģĹãģ¦
    -0.10
    äºĨ大éĩıçļĦ
    -0.10
    POSITIVE LOGITS
    æĪijä»¬åľ¨
    0.10
    å°ıç¼ĸ
    0.09
    ä¹İ
    0.09
     why
    0.08
    forth
    0.08
    为ä»Ģä¹Īè¦ģ
    0.08
    æĢİä¹Īèĥ½
    0.08
    å½ĵæĪij们
    0.08
    åIJĮåѦ们
    0.08
    o
    0.08
    Activations Density 0.035%

    No Known Activations