© 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. 52601
    Prev
    Next
    INDEX
    Explanations

    nationalities ending with -an, -ian, -onian

    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
    ullen
    -0.10
     Everybody
    -0.09
    ÑģÑĤво
    -0.09
    å¤§åĽ½
    -0.08
    åĽĽæĸ¹
    -0.08
    imum
    -0.08
    brace
    -0.08
    entication
    -0.08
    è¯įæĿ¡
    -0.08
    rollo
    -0.08
    POSITIVE LOGITS
    ç±į
    0.12
    -born
    0.10
    anian
    0.10
    çī¹æľīçļĦ
    0.10
    ians
    0.10
    ische
    0.10
    onian
    0.09
    æĿ¥çļĦ
    0.09
    å¢ĥåĨħ
    0.09
     native
    0.09
    Activations Density 0.353%

    No Known Activations