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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7648
    Prev
    Next
    INDEX
    Explanations

    water and its properties

    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
    è£ħæī®
    -0.10
    åħ¶æīĢ
    -0.09
    ä¸įäºĪ
    -0.09
    é³ı
    -0.09
    å¼ĢæĿ¥
    -0.09
    åĩ«
    -0.08
    ocab
    -0.08
    ãģ²ãģ¨ãĤĬ
    -0.08
     waterfall
    -0.08
    è¯Ī
    -0.08
    POSITIVE LOGITS
    falls
    0.10
    liche
    0.09
    loads
    0.08
    鹤
    0.08
     Chandler
    0.08
    missive
    0.08
    color
    0.08
    æ·±å¤Ħ
    0.08
    å§Ķ
    0.08
    shed
    0.07
    Activations Density 0.166%

    No Known Activations