© 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. 32294
    Prev
    Next
    INDEX
    Explanations

    by dates

    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¥ĩæĢª
    -0.09
    ä¸Ģåı°
    -0.09
    æĪIJçĨŁçļĦ
    -0.08
    åİĿ
    -0.08
    æľ¨åľ°æĿ¿
    -0.08
     поÑĤ
    -0.08
    åį°è±¡
    -0.08
    jen
    -0.08
    ãģ°ãģĭãĤĬ
    -0.08
     familiar
    -0.08
    POSITIVE LOGITS
    å´ĩé«ĺ
    0.10
    plib
    0.09
    ppers
    0.09
    建åĨĽ
    0.09
     phá»ķ
    0.09
     May
    0.09
    omap
    0.09
    å½ĵåľ°æŶéĹ´
    0.08
     hôm
    0.08
     lyon
    0.08
    Activations Density 0.019%

    No Known Activations