© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36934
    Prev
    Next
    INDEX
    Explanations

    intent or aim

    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
    èıĩ
    -0.09
    åİĭåĬĽ
    -0.09
    .GetItem
    -0.09
    legg
    -0.09
    çŁŃçŁŃ
    -0.08
    æ¼Ķ
    -0.08
    ocy
    -0.08
    cher
    -0.08
    ANGO
    -0.08
    çļĦä¸ĢéĿ¢
    -0.08
    POSITIVE LOGITS
    è¿ģ
    0.10
    两åı¥
    0.09
    æıIJè´¨
    0.09
    饮
    0.09
    æĮ¯åħ´
    0.08
    交ç»Ļ
    0.08
    éĩįæĸ°
    0.08
    å°Ĩåħ¶
    0.08
    ä¸ĭéĿ¢æĺ¯å°ı
    0.08
    æĹ©æĹ¥
    0.08
    Activations Density 0.035%

    No Known Activations