© 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. 37250
    Prev
    Next
    INDEX
    Explanations

    deformans, domains, spp

    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
    æĤ»
    -0.09
    pering
    -0.08
    åĴ½åĸī
    -0.08
    ç½¾
    -0.08
    æģĭæĥħ
    -0.08
    ä¸ĢåĽŀäºĭ
    -0.08
    Rgb
    -0.08
    éĺĬ
    -0.08
    ocale
    -0.08
    çļİ
    -0.08
    POSITIVE LOGITS
    _d
    0.26
     д
    0.23
    д
    0.22
    -d
    0.22
     D
    0.21
    ãĥī
    0.21
    .d
    0.21
    	d
    0.19
    _D
    0.19
    .D
    0.19
    Activations Density 0.465%

    No Known Activations