© 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. 56342
    Prev
    Next
    INDEX
    Explanations

    Vegas and related locations

    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
    èĥ¡åIJĮ
    -0.10
    æ´¥
    -0.09
    纵
    -0.09
    æ¤Ĵ
    -0.09
    åħħåĪĨåıijæĮ¥
    -0.09
    è¿Ļè¯Ŀ
    -0.09
     advoc
    -0.08
    éĺIJ
    -0.08
    åĻ©
    -0.08
    é¹ĥ
    -0.08
    POSITIVE LOGITS
     Vegas
    0.12
     Nevada
    0.11
    å¿ĺ
    0.10
     Resorts
    0.10
     vegas
    0.10
    æĭīæĸ¯
    0.10
     casinos
    0.09
    entifier
    0.09
    æĮ½
    0.09
    头
    0.09
    Activations Density 0.056%

    No Known Activations