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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58013
    Prev
    Next
    INDEX
    Explanations

    brand names and product descriptions

    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
    åĩ¿
    -0.08
    çļĦä¼łç»Ł
    -0.08
    é¦ĸåħĪæĺ¯
    -0.08
    åħ±åĪĽ
    -0.08
    é¦ĸåħĪ
    -0.08
    igt
    -0.08
    ä¸įä»ħä»ħæĺ¯
    -0.08
     prob
    -0.08
    èį·
    -0.08
    inar
    -0.07
    POSITIVE LOGITS
    æĬĹåĩ»
    0.10
     Welch
    0.09
    飾
    0.09
    åºĶçĶ¨æŁ¥çľĭ
    0.09
    éĻĦå±ŀ
    0.09
    饰
    0.09
    è¾¹ç¼ĺ
    0.08
    追踪
    0.08
     огÑĢани
    0.08
    igham
    0.08
    Activations Density 0.080%

    No Known Activations