© 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. 29692
    Prev
    Next
    INDEX
    Explanations

    an event or place

    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
    èĮĦåŃIJ
    -0.09
    家éķ¿ä»¬
    -0.09
    ä¸įæĸŃæıIJé«ĺ
    -0.09
    å°±åĮ»
    -0.09
    ön
    -0.09
    身边çļĦ
    -0.09
    åĮ»åѦéĻ¢
    -0.08
    åijĬè¯ī大家
    -0.08
    è¿Ļ件
    -0.08
    客åİħ
    -0.08
    POSITIVE LOGITS
    åĢĻ
    0.09
    æįŁ
    0.08
    åı«åģļ
    0.08
    åĪ©åĻ¨
    0.08
    лаг
    0.08
    çĪ°
    0.08
    ä¿į
    0.08
    еÑħ
    0.08
    azen
    0.08
    år
    0.08
    Activations Density 0.076%

    No Known Activations