© 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. 8643
    Prev
    Next
    INDEX
    Explanations

    speed limits, camera enforcement

    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
    积
    -0.10
    æ·Ģ
    -0.09
    åĩ»
    -0.09
    alous
    -0.09
    éĬ®
    -0.08
    ç©į
    -0.08
    åļı
    -0.08
    å°¼æĸ¯
    -0.08
    èı°
    -0.08
    羯
    -0.08
    POSITIVE LOGITS
    æĶ¸
    0.09
    illos
    0.09
    è¶ħ
    0.09
    å¦ĩ
    0.09
     authorities
    0.09
    .Expect
    0.09
     speeding
    0.08
    åįģ大
    0.08
    åĿij
    0.08
    éĢŁåº¦
    0.08
    Activations Density 0.054%

    No Known Activations