© 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. 18722
    Prev
    Next
    INDEX
    Explanations

    Algeria, Morocco, North Africa

    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
    çĶ¥
    -0.11
    è¾Ħ
    -0.11
    ÑĢей
    -0.10
    åĪį
    -0.10
    ãĤ·ãĥ³
    -0.09
    è¾Ļ
    -0.09
    æľ¬ç½ij
    -0.09
    æĭ¿åĩº
    -0.09
     florida
    -0.09
     canada
    -0.09
    POSITIVE LOGITS
    enes
    0.10
     Morocco
    0.09
    ouns
    0.09
     Bout
    0.09
    ä¿ĥ
    0.09
    æ¡ĤæŀĹ
    0.09
    èĬĻèĵī
    0.08
    éĿĻ
    0.08
    æ¦ľ
    0.08
    èµĶåģ¿
    0.08
    Activations Density 0.064%

    No Known Activations