© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9132
    Prev
    Next
    INDEX
    Explanations

    vision and blindness

    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
    PEG
    -0.09
    ç¾½
    -0.09
    æĶ¾å¼Ģ
    -0.08
    æīĺ管
    -0.08
    flip
    -0.08
    Indian
    -0.08
    亩
    -0.08
    æĬľ
    -0.08
    æĬµæĬĹ
    -0.08
     ÑĦакÑĤ
    -0.08
    POSITIVE LOGITS
    è§ĨåĬĽ
    0.20
    çļĦçľ¼çĿĽ
    0.17
    çľ¼çĿĽ
    0.16
    åıĮçľ¼
    0.15
     Sight
    0.15
     vision
    0.14
     blindness
    0.14
    çľ¼éĥ¨
    0.14
    çŀİ
    0.14
    åIJ¬åĬĽ
    0.14
    Activations Density 0.193%

    No Known Activations