© 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. 47986
    Prev
    Next
    INDEX
    Explanations

    Nevada

    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
    é²ł
    -0.09
    é½IJé²ģ
    -0.09
    ogen
    -0.09
    å¯Ŀ室
    -0.08
    éĵ°
    -0.08
    iesz
    -0.08
    éķĽ
    -0.08
    ings
    -0.08
    éĨį
    -0.08
    滤
    -0.08
    POSITIVE LOGITS
     Nevada
    0.14
     desert
    0.10
    åı¯æĥ³
    0.09
    éªĨ
    0.09
    éĦ¯
    0.09
     Desert
    0.09
    çĤ¼
    0.09
     Wah
    0.09
     Tahoe
    0.09
    åıĹçĽĬ
    0.09
    Activations Density 0.020%

    No Known Activations