© 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. 51709
    Prev
    Next
    INDEX
    Explanations

    photoresist or integrated circuits

    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
     Denied
    -0.09
    çıł
    -0.09
    åįĥéĩĮ
    -0.09
    æģ°
    -0.09
    NIC
    -0.08
    gua
    -0.08
    ongan
    -0.08
    ickt
    -0.08
    oller
    -0.08
    _cn
    -0.08
    POSITIVE LOGITS
    å°Ħ
    0.10
    åĭ¤åĬ³
    0.10
    ç»ıè¿ĩå¤ļå¹´
    0.09
    èµ°åĩº
    0.09
    æłİ
    0.09
    æĥ³äºĨ
    0.09
    设ç«ĭäºĨ
    0.09
    缸继
    0.09
    æķ´å½¢
    0.08
    è¶ħé«ĺ
    0.08
    Activations Density 0.290%

    No Known Activations