© 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. 55519
    Prev
    Next
    INDEX
    Explanations

    in locations and states

    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
    å·¾
    -0.10
     Chew
    -0.10
    æľ¬çĿĢ
    -0.09
     lá»ĩ
    -0.09
    å½ĵæŶçļĦ
    -0.09
    æĸ°æµª
    -0.09
    说æĪij
    -0.09
    suite
    -0.09
    ãģĦãģĨ
    -0.09
    tam
    -0.08
    POSITIVE LOGITS
    emann
    0.10
    å¤ļä¸ĩ
    0.09
    æĨĭ
    0.08
    ван
    0.08
    èĿĪ
    0.08
    确认
    0.08
    笼
    0.08
    æľīä¸ĢçĤ¹
    0.08
    urgent
    0.08
    å±ı
    0.08
    Activations Density 0.037%

    No Known Activations