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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49355
    Prev
    Next
    INDEX
    Explanations

    printing customization designs

    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
    ç¼Ĩ
    -0.08
    ãĥijãĤ¤
    -0.08
    èµĦ产éĩįç»Ħ
    -0.08
    aan
    -0.08
    ÙĪاء
    -0.07
    kers
    -0.07
    Larry
    -0.07
    кÑĥÑĢ
    -0.07
    贪婪
    -0.07
    豪åįİ
    -0.07
    POSITIVE LOGITS
    åį°åĪ·
    0.14
    æīĵåį°æľº
    0.13
     Designs
    0.12
    æī¹éĩı
    0.11
    Printing
    0.11
    åį°
    0.11
    customize
    0.11
    æīĵåį°
    0.11
     printing
    0.11
    åĪĽæĦı
    0.10
    Activations Density 0.073%

    No Known Activations