© 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. 32013
    Prev
    Next
    INDEX
    Explanations

    initials followed by surnames

    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
    秩
    -0.09
    ä½Ĩä¹Ł
    -0.09
    æĶ¶èİ·
    -0.08
    åIJĪ
    -0.08
    cock
    -0.08
    åIJĪèµĦ
    -0.08
    欢
    -0.08
     Respons
    -0.08
    çİĽ
    -0.08
    æ°ĵ
    -0.08
    POSITIVE LOGITS
    å§Ķ
    0.11
    说æĪij
    0.10
    éĹ®éĹ®
    0.10
    @js
    0.10
    å§Ķç»Ħç»ĩ
    0.09
    è¿Ļ个人
    0.09
    åľ¨åIJĮä¸Ģ
    0.09
    eam
    0.09
    åĪĹåħ¥
    0.09
    åı£ä¸Ń
    0.09
    Activations Density 0.271%

    No Known Activations