© 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. 10841
    Prev
    Next
    INDEX
    Explanations

    interior secretary, Energy Systems, Homeland Security, Health, environmental condition

    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
    åľĺ
    -0.11
    æīĴ
    -0.09
    åĽ¢
    -0.09
    upo
    -0.09
    adh
    -0.09
    å¸ĤæĶ¿åºľ
    -0.08
    æł·
    -0.08
    å°ĨæĿ¥
    -0.08
    è·¨å¢ĥ
    -0.08
    thr
    -0.08
    POSITIVE LOGITS
    åĪĿæģĭ
    0.10
    å¦į
    0.09
    IDL
    0.09
    çݺ
    0.09
     Vish
    0.09
    é«Ń
    0.09
    éļ¾é¢ĺ
    0.09
    çıij
    0.09
    éĹ²ç½®
    0.08
    åĿļ硬
    0.08
    Activations Density 0.107%

    No Known Activations