© 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. 38456
    Prev
    Next
    INDEX
    Explanations

    political leader titles

    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
     clos
    -0.10
    sonian
    -0.09
    åģģ
    -0.09
    -0.08
    ä¸įèµ·
    -0.08
    éĹº
    -0.08
    è¶ĬæĿ¥
    -0.08
    .um
    -0.08
    æ±īåŃIJ
    -0.08
     mó
    -0.08
    POSITIVE LOGITS
    ARAM
    0.09
    åĨ¥
    0.09
    éĿ¢åIJij
    0.09
    vr
    0.09
    æľŁéĹ´
    0.09
    èIJ¤
    0.09
    æĹ¶è®¸
    0.09
    ãģ¦ãģĦ
    0.08
    LIK
    0.08
    çļĦæłĩåĩĨ
    0.08
    Activations Density 0.109%

    No Known Activations