© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60899
    Prev
    Next
    INDEX
    Explanations

    campaign finance

    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
    æĪIJçĨŁ
    -0.09
    _CPU
    -0.09
    èįĴ
    -0.09
     Mature
    -0.09
    æ¥Ķ
    -0.08
    uil
    -0.08
    é»ijèī²
    -0.08
    è¯ł
    -0.08
    åħ±çĶŁ
    -0.08
    人æīį
    -0.08
    POSITIVE LOGITS
    è¡Įè´¿
    0.10
    ç»ıè´¹
    0.10
    è´º
    0.09
    èµĦåĬ©
    0.09
    campaign
    0.09
    è´¿
    0.09
    æĶ¿æ²»
    0.09
     campaign
    0.09
    åħļ
    0.09
    饮
    0.08
    Activations Density 0.090%

    No Known Activations