© 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. 8866
    Prev
    Next
    INDEX
    Explanations

    create something

    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
    еÑĢи
    -0.10
    è¿Ļä¸įæĺ¯
    -0.09
    好äºĭ
    -0.09
    .Actor
    -0.09
    çģµæ°Ķ
    -0.08
    mát
    -0.08
    å§Ĩ
    -0.08
    ä»ĸ们
    -0.08
    èİ«æĸ¯
    -0.08
    亮丽
    -0.08
    POSITIVE LOGITS
    ä¸ĸ人
    0.09
    客æĪ·æıIJä¾Ľ
    0.08
    _viewer
    0.08
    让人
    0.08
    ÐĿÐķ
    0.08
    __$
    0.08
    æĪij们è¦ģ
    0.08
    è¯ķåĽ¾
    0.08
    Scheme
    0.08
    ç±´
    0.08
    Activations Density 0.128%

    No Known Activations