© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37051
    Prev
    Next
    INDEX
    Explanations

    is/are/was followed by a noun phrase

    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
    ÅĦ
    -0.09
    ulis
    -0.09
    æĹģ
    -0.08
    itta
    -0.08
    ropy
    -0.08
     Alison
    -0.08
    æ³¢çī¹
    -0.08
    ritis
    -0.08
    itus
    -0.08
    _scal
    -0.08
    POSITIVE LOGITS
    åIJĦç§į
    0.11
    éĤ£ç§į
    0.10
    åIJĦç§įåIJĦæł·
    0.10
    è¿Ļæł·ä¸Ģ个
    0.10
    æŃ¥ä¼IJ
    0.10
    ä¸Ģ个éĩįè¦ģ
    0.09
    羣å®ŀæĢ§
    0.09
    è¦ģèĢĥèĻij
    0.09
    ä¸Ŀ毫
    0.09
    äºĭçī©
    0.09
    Activations Density 0.023%

    No Known Activations