© 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. 20562
    Prev
    Next
    INDEX
    Explanations

    visual and environmental perception

    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
    æ²®
    -0.11
     closet
    -0.09
    Fully
    -0.09
     Fully
    -0.09
    å§ĭ
    -0.09
    è¿ĺæĥ³
    -0.09
    奥巴
    -0.09
    å¼ĢæĶ¾å¼ı
    -0.09
    ç¬ĶèĢħ
    -0.09
    éĿ©
    -0.08
    POSITIVE LOGITS
    è§ħ
    0.10
    åľ°è²Į
    0.10
    åħ¥åı£
    0.09
    线索
    0.09
    çļĦæĥħ
    0.09
    çĥĤ
    0.08
     cues
    0.08
    DataProvider
    0.08
    çݯå¢ĥä¸Ń
    0.08
    landscape
    0.08
    Activations Density 0.293%

    No Known Activations