© 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. 23709
    Prev
    Next
    INDEX
    Explanations

    between October

    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
    è¾ĥ为
    -0.10
     somewhat
    -0.09
    åľ¨æѤä¹ĭåīį
    -0.09
    åħ¶æīĢ
    -0.08
    è¿ĩäºİ
    -0.08
     oneself
    -0.08
    诸
    -0.08
    ç¬ĶèĢħ
    -0.08
    3
    -0.08
     Vers
    -0.08
    POSITIVE LOGITS
    æĬĬä½ł
    0.14
    å¸®ä½ł
    0.13
    å¯¹ä½ł
    0.13
    è®©ä½ł
    0.13
    ãģĤãģªãģŁãģ®
    0.12
    æĺ¯ä½ł
    0.12
    ä½łçļĦ
    0.12
    ãģłãģ£ãģ¦
    0.12
    è·Łä½ł
    0.12
    ä¸ºä½ł
    0.11
    Activations Density 0.412%

    No Known Activations