© 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. 7073
    Prev
    Next
    INDEX
    Explanations

    worldwide countries prevalence adopted questionnaire investigation

    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
    æ¹Ł
    -0.11
    æīĵè¿Ľ
    -0.09
    åĩłæ¬¡
    -0.09
    åĢĺ
    -0.09
    дол
    -0.08
    åĿIJåľ¨
    -0.08
    çĶŁäº§åĴĮ
    -0.08
    æ¡ħ
    -0.08
    æĺ¯ä¸Ģä½į
    -0.08
    çĥĻ
    -0.08
    POSITIVE LOGITS
    åIJĦåľ°
    0.19
    çľģ份
    0.16
    åIJĦçľģ
    0.16
    åIJĦåİ¿
    0.15
     cities
    0.14
    纷纷
    0.14
     countries
    0.14
    åľ°åĮºçļĦ
    0.14
    åŁİå¸ĤçļĦ
    0.13
    åľ°åĮº
    0.13
    Activations Density 0.175%

    No Known Activations