© 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. 31834
    Prev
    Next
    INDEX
    Explanations

    this followed by a noun

    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
    æĶ¾çľ¼
    -0.09
    æľīæĽ´å¥½çļĦ
    -0.09
    æĺ¯å¯¹
    -0.09
    witter
    -0.08
    好人
    -0.08
    ä¹Łä¸į
    -0.08
    çī¹åĪ«æĺ¯
    -0.08
    æĽ´æĺ¯
    -0.08
    å¥ī
    -0.08
    å¼Ħå¾Ĺ
    -0.08
    POSITIVE LOGITS
    éĥ¨ä»½
    0.09
     Gree
    0.09
    że
    0.09
     particular
    0.09
    è¿Ļéĥ¨åĪĨ
    0.09
     part
    0.09
     fir
    0.09
    å§Ĵ
    0.09
    éĩįè¦ģçļĦ
    0.08
    åij±
    0.08
    Activations Density 0.220%

    No Known Activations