© 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. 11194
    Prev
    Next
    INDEX
    Explanations

    US States, Cities, and places

    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
    ä¸ĸä¿Ĺ
    -0.10
    æİ¥è¿ij
    -0.09
    æ±ľ
    -0.08
    éĨī
    -0.08
    çĪĨ
    -0.08
    åıĪ好åıĪ
    -0.08
     Paulo
    -0.08
    à¹ģà¸ļà¸ļ
    -0.08
    æĿĸ
    -0.07
     пÑĢоведен
    -0.07
    POSITIVE LOGITS
    ä¸ĢèĦļ
    0.10
    çļĦç¡®
    0.10
    èµ·é£ŀ
    0.09
    å¤Ħå¤Ħ
    0.09
    æĹ»
    0.09
    ä¹ĭæĹħ
    0.08
    ä¸ĢåĪĢ
    0.08
    orthy
    0.08
    æĹħéĢĶ
    0.08
    åĮ£
    0.08
    Activations Density 0.063%

    No Known Activations