© 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. 36693
    Prev
    Next
    INDEX
    Explanations

    code delimiters and punctuation

    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
    åĮĸçļĦ
    -0.08
    çĻ«çĹ«çĹħ
    -0.07
     Winds
    -0.07
    èĩ³ä¸Ĭ
    -0.07
    ÙĤد
    -0.07
    ADF
    -0.07
    æŁIJ
    -0.07
    ibr
    -0.07
    adium
    -0.07
    æĪĸèĢħ说
    -0.07
    POSITIVE LOGITS
    çŃīçŃī
    0.10
    éķ¿çŁŃ
    0.10
    è¿ĻäºĽéĥ½æĺ¯
    0.09
    绣绣
    0.09
    æĥ®
    0.09
    @qq
    0.09
    好人
    0.09
    åIJĦç§į
    0.09
    æĹłä¸į
    0.09
    ä¸Ģç§Ĵ
    0.08
    Activations Density 0.156%

    No Known Activations