© 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. 8224
    Prev
    Next
    INDEX
    Explanations

    atop or aboard

    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
    t
    -0.09
    ãĥ¼ãĤ¸
    -0.09
    çīĮåŃIJ
    -0.09
    éģ½
    -0.09
    i
    -0.08
    аÑĢÑĮ
    -0.08
    åĩºèº«
    -0.08
    æĽĿ
    -0.08
    alking
    -0.08
    %%%
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.11
    ä¸Ģå®ļçļĦ
    0.11
    /on
    0.11
    åIJĦç§į
    0.10
    çİĩè¾¾
    0.10
    ä½ķå¤Ħ
    0.10
    åĪ«äººçļĦ
    0.10
    _OW
    0.09
    人们çļĦ
    0.09
    åįłæį®
    0.09
    Activations Density 0.008%

    No Known Activations