© 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. 55753
    Prev
    Next
    INDEX
    Explanations

    nonsteroidal anti-inflammatory

    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
    åĩĨ
    -0.09
    ople
    -0.08
    ously
    -0.08
    lander
    -0.08
    ãģ®ãģ¯
    -0.08
    éĥ
    -0.08
    使å¾Ĺ
    -0.08
    aneously
    -0.08
    ÙĨاÙĨ
    -0.08
    åIJĦ个æĸ¹éĿ¢
    -0.08
    POSITIVE LOGITS
    ÅĽl
    0.09
    ful
    0.08
    /function
    0.08
    åĽĽçº§
    0.08
    Ñĭва
    0.08
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.08
    auty
    0.08
    èµĦ产管çIJĨ
    0.08
    æī§ä¸ļ
    0.08
    Sac
    0.07
    Activations Density 0.524%

    No Known Activations