© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8943
    Prev
    Next
    INDEX
    Explanations

    world states and transformations

    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
    åĵªæĢķ
    -0.10
    è¿Ħä»Ĭ
    -0.10
    åīĸæŀIJ
    -0.09
    åİĤ
    -0.09
    çͳ
    -0.09
    主åĬ¨æĢ§
    -0.09
    æĹ¶è¡¨ç¤º
    -0.09
    å®ģæĦ¿
    -0.09
    å°±è¶Ĭ
    -0.09
    é³ĥ
    -0.09
    POSITIVE LOGITS
    ä¸įåĨįæĺ¯
    0.10
    仿
    0.10
    å¤įåı¤
    0.09
    ä¸įåĨį
    0.09
    (super
    0.08
    人å¿ĥ
    0.08
     tra
    0.08
    æ··åIJĪ
    0.08
     unknown
    0.08
    licht
    0.08
    Activations Density 0.076%

    No Known Activations