© 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. 7086
    Prev
    Next
    INDEX
    Explanations

    special characters and code constructs

    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
    ä½°
    -0.09
    èµĺ
    -0.09
    æĦıä¹īä¸ĬçļĦ
    -0.09
    ä¸įåı¯æĪĸ缺
    -0.09
    rapper
    -0.09
     Kut
    -0.09
    æ¤Ĵ
    -0.09
    anson
    -0.09
    åij½è¿IJ
    -0.09
    phans
    -0.09
    POSITIVE LOGITS
    ever
    0.09
    æīĭä¸Ń
    0.09
    tlement
    0.08
    ../../../
    0.08
    entication
    0.08
    èĢĮ导èĩ´
    0.08
    odore
    0.08
    :init
    0.08
    /testing
    0.08
    ÑįÑĤомÑĥ
    0.08
    Activations Density 1.099%

    No Known Activations