© 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. 33946
    Prev
    Next
    INDEX
    Explanations

    places within US names

    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
    éĽĨä¸Ńåľ¨
    -0.11
    ä½ľä¸ºä¸Ģç§į
    -0.10
     SAN
    -0.10
    è¥Ħ
    -0.09
     moda
    -0.09
    è¿ĩåIJİ
    -0.09
    好åĿı
    -0.09
    天ä¸Ĭ
    -0.09
    æĸ¼æĺ¯
    -0.08
    çĬĴ
    -0.08
    POSITIVE LOGITS
    èĮħ
    0.09
    å½ĺ
    0.08
     mainland
    0.08
    à¹ģà¸Ķà¸ĩ
    0.08
     Shore
    0.08
    è¾°
    0.08
    ama
    0.08
    éĻħ
    0.08
    çļĦçľ¼
    0.08
    enn
    0.08
    Activations Density 0.083%

    No Known Activations