© 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. 51748
    Prev
    Next
    INDEX
    Explanations

    open doors or windows

    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
    伤
    -0.09
    对æīĭ
    -0.09
    èĦ¸èī²
    -0.08
    æĬķèµĦé¢Ŀ
    -0.08
    ç¥ŀæĥħ
    -0.08
     stamps
    -0.08
    éī´å®ļ
    -0.08
    itsu
    -0.08
    iese
    -0.08
    è·Łè¸ª
    -0.08
    POSITIVE LOGITS
    å¼ĢæĶ¾
    0.17
    æīĵå¼Ģ
    0.17
    æķŀå¼Ģ
    0.16
    å¼ĢçĿĢ
    0.16
    æīĵå¼ĢäºĨ
    0.16
     doors
    0.16
     open
    0.15
    æķŀ
    0.15
    éŨçªĹ
    0.15
     Doors
    0.15
    Activations Density 0.166%

    No Known Activations