© 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. 6929
    Prev
    Next
    INDEX
    Explanations

    cancer cells vs normal cells

    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
     Ðijа
    -0.10
    æĪIJåIJį
    -0.09
    顶
    -0.09
    æĤ¬
    -0.09
    èIJİ
    -0.09
    ä¸Ģ个æĸ°çļĦ
    -0.09
    æīĵ好
    -0.08
    åı³è¾¹
    -0.08
    è²Į
    -0.08
    å²Ń
    -0.08
    POSITIVE LOGITS
    _SW
    0.10
     Monaco
    0.10
    åŃĹæł·
    0.10
    æ´¥
    0.09
    çĻĮ
    0.09
    æݨéĶĢ
    0.09
    å¹¼ç¨ļ
    0.09
    åı¯ä»¥è¯´æĺ¯
    0.09
     Pets
    0.09
    Ñħа
    0.09
    Activations Density 0.170%

    No Known Activations