© 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. 9022
    Prev
    Next
    INDEX
    Explanations

    camping and sleeping equipment

    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
    æīĺ
    -0.09
    楼ä¸ĭ
    -0.09
    ä¸ĬäºĨ
    -0.08
    abar
    -0.08
    оÑĤоÑĢ
    -0.08
    elf
    -0.08
     onboard
    -0.08
    伤
    -0.08
    ãĥ¼ãĤ·
    -0.08
    D
    -0.08
    POSITIVE LOGITS
    å¸IJ篷
    0.17
     tents
    0.12
    èIJ¥åľ°
    0.12
     tent
    0.12
    æ´¹
    0.11
    tent
    0.10
    帳
    0.10
     camps
    0.10
    멸
    0.10
    éĶħ
    0.10
    Activations Density 0.053%

    No Known Activations