© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52963
    Prev
    Next
    INDEX
    Explanations

    children and adolescents

    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
    æ¡ħ
    -0.10
    åŃ©åŃIJ们
    -0.10
    äºĴ缸
    -0.10
    让åŃ©åŃIJ
    -0.09
    advance
    -0.09
    é¢Ħå®ļ
    -0.09
    æ¯Ĺ
    -0.09
    epad
    -0.09
    èĭ´
    -0.09
    æ°ijçĶŁ
    -0.09
    POSITIVE LOGITS
    ACS
    0.08
    尤为
    0.08
     ÙģÙĪÙĤ
    0.08
     Spicer
    0.08
     باÙĦØ¥
    0.08
    ä¸Ĭãģ®
    0.08
    èĩ¾
    0.08
    CHA
    0.08
     bicycle
    0.08
    squ
    0.08
    Activations Density 0.031%

    No Known Activations