© 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. 52661
    Prev
    Next
    INDEX
    Explanations

    both ... and

    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
    è¿Ļ两个
    -0.10
    两次
    -0.09
    欢è¿İæĤ¨
    -0.09
     both
    -0.09
    arna
    -0.09
    éľĪ
    -0.09
    ä¼ĺæĥłæĶ¿çŃĸ
    -0.09
    è¿Ļ两
    -0.08
    å®£ä¼łæ´»åĬ¨
    -0.08
    åĸ·
    -0.08
    POSITIVE LOGITS
    oom
    0.11
    æİ·
    0.10
     moll
    0.08
    åĵ¥ä»¬
    0.08
    çļĦæĸ¹å¼ıæĿ¥
    0.08
    çł¥
    0.08
    éķ¿éķ¿
    0.08
    OSC
    0.08
     slugg
    0.08
    ä½ľä¸ºä¸ĢåIJį
    0.08
    Activations Density 0.026%

    No Known Activations