© 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. 23922
    Prev
    Next
    INDEX
    Explanations

    embassy or consulate in

    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
    нÑı
    -0.10
    æµĨ
    -0.09
     arty
    -0.09
    ä¸įæĿ¥
    -0.09
    èħ¾é£ŀ
    -0.09
    æĸ¹ä½į
    -0.09
     McGill
    -0.09
    lays
    -0.08
    æĸ¹æīį
    -0.08
    çī¹èī²çļĦ
    -0.08
    POSITIVE LOGITS
    UNE
    0.09
    HING
    0.08
    é«ĺæĢ§èĥ½
    0.08
    è°³
    0.08
    èī²å½©
    0.08
    ä½
    0.08
    Compound
    0.08
    rug
    0.08
    że
    0.08
    inkel
    0.08
    Activations Density 0.009%

    No Known Activations