© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36009
    Prev
    Next
    INDEX
    Explanations

    introduces or grants or orders

    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
    åĩłä¹İ
    -0.10
    åĩłä¹İæĺ¯
    -0.10
    å¹¾ä¹İ
    -0.09
    å¤ļå¹´åīį
    -0.09
    ording
    -0.09
     ساب
    -0.08
     probably
    -0.08
    çī¹æĿĥ
    -0.08
    almost
    -0.08
    éģĵ
    -0.08
    POSITIVE LOGITS
    ä¸ĩä¸Ģ
    0.14
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.13
    è¶³å¤Ł
    0.13
    ä¸Ģå¦Ĥ
    0.12
    è¶³å¤ŁçļĦ
    0.12
    æĺİå¹´
    0.12
    æĪĸåħ¶ä»ĸ
    0.12
    å±ĬæŶ
    0.12
    继ç»Ńä¿ĿæĮģ
    0.11
    è¿Ļæł·çļĦè¯Ŀ
    0.11
    Activations Density 0.068%

    No Known Activations