© 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. 5855
    Prev
    Next
    INDEX
    Explanations

    valley, Arkansas, Noida, Lakeway, Lake

    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
    èĥ¡åIJĮ
    -0.09
    骢
    -0.09
    ä¼łç»Łäº§ä¸ļ
    -0.09
    京
    -0.09
    trad
    -0.09
     traditional
    -0.08
    åħħå½ĵ
    -0.08
     Shelter
    -0.08
     heir
    -0.08
     coast
    -0.08
    POSITIVE LOGITS
    icens
    0.10
    失
    0.10
    åħ±è¯Ĩ
    0.10
    инÑĦ
    0.09
    æ¶Ķ
    0.09
    ä¸įä¿¡
    0.09
    NSE
    0.09
    æĸ°åĮº
    0.09
    èĤ
    0.09
     chÃło
    0.09
    Activations Density 0.071%

    No Known Activations