© 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. 4981
    Prev
    Next
    INDEX
    Explanations

    California districts and agencies

    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
     California
    -0.12
    åĽĽå·Ŀçľģ
    -0.12
    California
    -0.10
    åĬłå·ŀ
    -0.10
    æĪIJéĥ½
    -0.10
    åħ¨æĹ¥åĪ¶
    -0.10
     Pacific
    -0.09
     Californ
    -0.09
     Oregon
    -0.09
     Hawaii
    -0.09
    POSITIVE LOGITS
    ENN
    0.10
    iard
    0.09
    æľIJ
    0.09
    ä¸įæĪIJ
    0.09
     Gingrich
    0.09
    ä¸Ĭä¸ĭ
    0.09
    ä¿Ħä¹Į
    0.09
     Mattis
    0.09
    .MON
    0.09
     Demp
    0.09
    Activations Density 0.135%

    No Known Activations