© 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. 55721
    Prev
    Next
    INDEX
    Explanations

    data analysis, acquisition, processing

    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
    åıijåĩº
    -0.09
    对æīĭ
    -0.09
    åħ¬åħ±èµĦæºIJ
    -0.09
    åij½é¢ĺ
    -0.08
    è¿Ļåıª
    -0.08
    çĽĸ
    -0.08
    MM
    -0.08
    æĻºåĬĽ
    -0.08
    æĻ®æŁ¥
    -0.08
    èĵĭ
    -0.08
    POSITIVE LOGITS
     data
    0.11
    æķ°æį®
    0.10
     datas
    0.10
    éªł
    0.10
     Data
    0.09
    logs
    0.09
    ãĥĩãĥ¼ãĤ¿
    0.09
    Data
    0.09
    åĪĨæŀIJ
    0.09
    åıĭåĸĦ
    0.09
    Activations Density 0.222%

    No Known Activations