© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52652
    Prev
    Next
    INDEX
    Explanations

    experience

    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
    趣åij³
    -0.09
    apped
    -0.09
    edException
    -0.09
    cade
    -0.09
    edList
    -0.09
    åľ°åĮºçļĦ
    -0.08
     Affairs
    -0.08
    çľ¼åīįçļĦ
    -0.08
    èĦ±èIJ½
    -0.08
     à¹Ĩ
    -0.08
    POSITIVE LOGITS
    mmo
    0.10
    åįģ足
    0.09
    able
    0.09
    abilit
    0.09
    odem
    0.09
    è²Ŀ
    0.09
    æĸŃè£Ĥ
    0.09
    ãģĹãĤĩãģĨ
    0.09
     SimpleName
    0.08
    ãģľ
    0.08
    Activations Density 0.015%

    No Known Activations