© 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. 6456
    Prev
    Next
    INDEX
    Explanations

    West Africa countries and security

    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
    岫
    -0.09
     Misc
    -0.09
    帽
    -0.09
    äºĨä¸Ģåı£
    -0.09
    åıijæĸĩ
    -0.08
    亿ä¸ĩ
    -0.08
    éĤij
    -0.08
    æ³
    -0.08
    ä¸ĭåįķ
    -0.08
    èĽ¤
    -0.08
    POSITIVE LOGITS
    éĿŀæ´²
    0.11
     Niger
    0.10
     African
    0.10
     Affero
    0.10
     Nigeria
    0.09
     prohib
    0.09
    Africa
    0.09
    AFE
    0.09
     african
    0.09
    诲
    0.09
    Activations Density 0.206%

    No Known Activations