© 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. 33669
    Prev
    Next
    INDEX
    Explanations

    friend, by, cheap, glorious, loyal, mere

    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
    å«£
    -0.10
    quier
    -0.10
    å¿Ļ
    -0.09
    åģı好
    -0.08
    ç¦ģ
    -0.08
    ä¾Ī
    -0.08
    ä¸Ĭå®ĺ
    -0.08
    åĢĮ
    -0.08
    #End
    -0.08
    gap
    -0.08
    POSITIVE LOGITS
    å¤ļä¹Ī
    0.09
    æĥħèĬĤ
    0.09
    æŃ¤äºº
    0.09
    éªĪ
    0.09
    ä¼Łå¤§çļĦ
    0.09
    é«ĺå°ļ
    0.09
    éĤªæģ¶
    0.09
    åłķ
    0.09
    /respond
    0.09
    ä¼Łå¤§
    0.09
    Activations Density 0.203%

    No Known Activations