© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7969
    Prev
    Next
    INDEX
    Explanations

    Central American countries and politics

    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
    ç¾Ĭæ¯Ľ
    -0.09
    spb
    -0.09
    åįĹéĿŀ
    -0.09
    éĺ¶æ¢¯
    -0.09
    rotein
    -0.08
    çĤ«
    -0.08
     Beats
    -0.08
    滨海
    -0.08
    å¾ģ
    -0.08
    raud
    -0.08
    POSITIVE LOGITS
     Hond
    0.11
     Nicaragua
    0.10
     Honduras
    0.10
    åĨĴ
    0.09
     Backpack
    0.09
    паÑģ
    0.09
     Guatemala
    0.09
    就读
    0.09
    åģ¶
    0.09
     Nicar
    0.09
    Activations Density 0.055%

    No Known Activations