© 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. 7733
    Prev
    Next
    INDEX
    Explanations

    positive adjectives

    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
    aires
    -0.10
    åij½åIJį为
    -0.09
    éĤ£ä¹Īå¤ļ
    -0.09
    诸å¦Ĥ
    -0.08
    åĵªæĢķ
    -0.08
    è¿Ļä¹Īå¤ļ
    -0.08
    ä¸Ģéģį
    -0.08
    éĻ¢
    -0.08
    ampa
    -0.08
    ä¸įèĩ³äºİ
    -0.08
    POSITIVE LOGITS
    é̏
    0.10
    çļĦä¾ĭåŃIJ
    0.10
    åħ¨æĹ¥
    0.10
    ä¸įéĶĻ
    0.09
    ä¸įéĶĻçļĦ
    0.09
    åħ¨æĹ¥åζ
    0.09
     newcom
    0.09
     manh
    0.09
    ayers
    0.09
     versatile
    0.09
    Activations Density 0.305%

    No Known Activations