© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8421
    Prev
    Next
    INDEX
    Explanations

    countries and administrative regions

    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
    亲
    -0.11
     гÑĢаж
    -0.10
    åı°å·ŀ
    -0.10
    åĽŀæĿ¥
    -0.10
    ç»įåħ´
    -0.09
    æ³°å·ŀ
    -0.09
     Smy
    -0.09
     Baldwin
    -0.09
    æĺ¯ä¸Ģä»¶
    -0.09
    ree
    -0.09
    POSITIVE LOGITS
     Uganda
    0.10
    ownik
    0.09
    åħĪ导
    0.09
    oser
    0.08
    anford
    0.08
     Abram
    0.08
    ingt
    0.08
    ModelProperty
    0.08
    inue
    0.08
     honors
    0.08
    Activations Density 0.067%

    No Known Activations