© 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. 51558
    Prev
    Next
    INDEX
    Explanations

    chain breaker, internal spring, Flying Ace, frame

    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
    åĭĩæķ¢
    -0.11
    主åħ¬
    -0.10
    .truth
    -0.10
    èĥĿ
    -0.10
    深深çļĦ
    -0.10
    æĤ£ä¸Ĭ
    -0.10
    æĿŀ
    -0.09
    çĬĢ
    -0.09
    鸱
    -0.09
    åħ±èµ¢
    -0.09
    POSITIVE LOGITS
    润æ»ij
    0.09
    Hack
    0.09
    åĿı
    0.09
    å¹²äºĭ
    0.08
    æŀ¢çº½
    0.08
    OP
    0.08
     lubric
    0.08
    دا
    0.08
    éĵ¾
    0.08
    kö
    0.08
    Activations Density 0.126%

    No Known Activations