© 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. 58860
    Prev
    Next
    INDEX
    Explanations

    phone numbers in parentheses

    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
    lyn
    -0.10
    лин
    -0.09
    ulin
    -0.08
    çĦī
    -0.08
    å·´æĸ¯
    -0.08
    æĹº
    -0.08
    umin
    -0.08
    uder
    -0.08
     deb
    -0.08
    fully
    -0.08
    POSITIVE LOGITS
    çªł
    0.08
    æłĹ
    0.08
    è¿Ļæł·ä¸Ģ
    0.08
     اÙĦعرب
    0.08
    åīįè¿°
    0.08
    emark
    0.08
    å¤ļæĸ¹
    0.08
    å¸ļ
    0.08
    宪
    0.08
    /effects
    0.08
    Activations Density 0.087%

    No Known Activations