© 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. 54066
    Prev
    Next
    INDEX
    Explanations

    quoted as saying

    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
    indo
    -0.10
    被è§Ĩ为
    -0.09
    æµģãĤĮ
    -0.09
    ãģ¾ãģķ
    -0.09
    å¹²éĥ¨éĺŁä¼į
    -0.08
     Pok
    -0.08
     hans
    -0.08
    çĬ¶åħĥ
    -0.08
    起身
    -0.08
    æıĸ
    -0.08
    POSITIVE LOGITS
    æľīè¿Ļæł·çļĦ
    0.11
    åģļçļĦ
    0.10
    anteed
    0.09
    åģļä¸ĢäºĽ
    0.09
    åģļè¿ĩ
    0.09
    åīįæĸ¹
    0.09
    è¿Ļæł·è¯´
    0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    0.09
    æĺ¥å¤ı
    0.09
    adius
    0.09
    Activations Density 0.016%

    No Known Activations