© 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. 5863
    Prev
    Next
    INDEX
    Explanations

    president names

    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
    æĢ»éĥ¨
    -0.09
    åħļå§Ķ
    -0.09
    主æĮģ人
    -0.09
    åĽ¹
    -0.09
    æIJŃä¹ĺ
    -0.09
    åѦåijĺ
    -0.08
    uit
    -0.08
    èĢĥä¸Ĭ
    -0.08
    éĩĮæĸ¯
    -0.08
    èŀŁ
    -0.08
    POSITIVE LOGITS
    ITT
    0.12
    ow
    0.10
    éĻĽ
    0.10
    ograd
    0.09
    身边
    0.09
    eten
    0.09
    nen
    0.09
    èĬĤèĥ½åĩıæİĴ
    0.09
     fir
    0.08
    æ½Ĩ
    0.08
    Activations Density 0.028%

    No Known Activations