© 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. 37822
    Prev
    Next
    INDEX
    Explanations

    living abroad or traveling

    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
    å¤ĸåĮħ
    -0.10
    æĿ¥èĩªäºİ
    -0.10
    åĩºçİ°åľ¨
    -0.10
    alker
    -0.09
    ching
    -0.08
    æĬľ
    -0.08
    weise
    -0.08
    ail
    -0.08
    ifer
    -0.08
    Ïį
    -0.08
    POSITIVE LOGITS
    -facing
    0.12
    ships
    0.10
    çĶ¥
    0.10
    åŀł
    0.10
    人士
    0.09
    ness
    0.09
     اÙĦتÙĪÙĨ
    0.09
    /off
    0.09
    acus
    0.09
    å·²ä¹ħ
    0.09
    Activations Density 0.005%

    No Known Activations