© 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. 33833
    Prev
    Next
    INDEX
    Explanations

    unemployment benefits and claims

    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
     Midnight
    -0.10
     bend
    -0.09
    éĵŃè®°
    -0.09
     ÐŁÐµÑĢе
    -0.09
    æ´ŀ
    -0.09
    éħįåIJĪ
    -0.09
    åĩºåħ¥
    -0.09
    é©®
    -0.09
    hei
    -0.09
    å»łåķĨ
    -0.09
    POSITIVE LOGITS
    社ä¼ļä¿Ŀéļľ
    0.15
    失ä¸ļ
    0.13
    ç¦ıåĪ©
    0.13
     unemployment
    0.12
    社ä¿Ŀ
    0.11
    åħ»èĢģéĩij
    0.11
    ä½İä¿Ŀ
    0.11
    æķijåij½
    0.10
     municipal
    0.10
    å¾ħéģĩ
    0.10
    Activations Density 0.106%

    No Known Activations