© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29393
    Prev
    Next
    INDEX
    Explanations

    "ancient" or "beginning"

    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
    Negative Logits
    è¿ĩæĿ¥
    -0.09
    åĵ¨
    -0.09
    主宰
    -0.09
    _FS
    -0.08
    èµĭ
    -0.08
    igan
    -0.08
    èµĭäºĪ
    -0.08
    åĬ©æĶ»
    -0.08
    åħĪ导
    -0.08
    èĩªçĦ¶
    -0.08
    POSITIVE LOGITS
    åħ´èµ·
    0.10
    .jet
    0.09
    润
    0.09
    æµģä¼ł
    0.09
    åĩŃçĿĢ
    0.09
    acks
    0.09
    æķ£
    0.08
    潤
    0.08
    unu
    0.08
    çĶŁæ´»æĸ¹å¼ı
    0.08
    Activations Density 0.052%

    No Known Activations