© 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. 30706
    Prev
    Next
    INDEX
    Explanations

    locations and entities

    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
    èĩªèº«çļĦ
    -0.12
    æīĭä¸ŃçļĦ
    -0.11
    èĩªå·±çļĦ
    -0.11
    失åİ»äºĨ
    -0.10
    åģ¥
    -0.10
    åIJĦæĸ¹
    -0.09
    èĩªèº«
    -0.09
    ETERS
    -0.09
    çĶ©
    -0.09
    æīĭä¸Ń
    -0.09
    POSITIVE LOGITS
    æĭ¿æĿ¥
    0.09
     bamboo
    0.08
    工信éĥ¨
    0.08
    æķ¦çħĮ
    0.08
    аÑĢи
    0.08
    èIJ¸
    0.08
    âĹĢ
    0.08
    åĴĮæľįåĬ¡
    0.08
    竹
    0.08
     Crush
    0.08
    Activations Density 0.125%

    No Known Activations