© 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. 10184
    Prev
    Next
    INDEX
    Explanations

    Pueblo Indians, County, Veterans

    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
    窣
    -0.09
     acrylic
    -0.08
    alytics
    -0.08
    ç¼ħ
    -0.08
    ´Ģ
    -0.08
    çIJĨçĶ±
    -0.08
     Ñĥказ
    -0.08
    ERA
    -0.08
    åħ¼èģĮ
    -0.08
    sole
    -0.08
    POSITIVE LOGITS
    ged
    0.10
    angelo
    0.10
    ãģĹãģı
    0.09
    æĢģ度
    0.09
    shima
    0.09
    å¢ĥçķĮ
    0.09
    lingen
    0.09
    é³Ĺ
    0.08
    ä½Ĩè¿Ļ
    0.08
    éĻŁ
    0.08
    Activations Density 0.003%

    No Known Activations