© 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. 30416
    Prev
    Next
    INDEX
    Explanations

    carries dependency

    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
    çĨ¨
    -0.10
    äºĨèĩªå·±çļĦ
    -0.10
    驽
    -0.09
    äºĶå®ĺ
    -0.09
    äºĨä¸Ģ份
    -0.09
    rol
    -0.09
    ç½ħ
    -0.09
    é¼·
    -0.09
    æĺİçıł
    -0.08
    ä¸ĢåĪ»
    -0.08
    POSITIVE LOGITS
    åĽŀ头
    0.09
    pire
    0.09
    anium
    0.09
    itos
    0.08
    èī°èĭ¦
    0.08
     cul
    0.08
    æĸĩåĮĸåĴĮ
    0.08
    با
    0.08
    odiac
    0.08
    æĶ¯
    0.08
    Activations Density 0.126%

    No Known Activations