© 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. 52129
    Prev
    Next
    INDEX
    Explanations

    personal opinions and views

    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
    ãĤ¾
    -0.10
    عار
    -0.09
    åıĹçĽĬ
    -0.09
     пÑĢид
    -0.09
    ç§ĺ书
    -0.09
    æĤĦæĤĦ
    -0.08
    yah
    -0.08
    ooter
    -0.08
    ован
    -0.08
     Jarvis
    -0.08
    POSITIVE LOGITS
    æĪij们认为
    0.22
    æĪij认为
    0.21
    ä»ĸ认为
    0.19
    åľ¨æĪijçľĭæĿ¥
    0.19
    æĪijè§īå¾Ĺ
    0.18
    认为
    0.16
    æĪij以为
    0.15
    æĪijçľĭ
    0.14
    ç¬ĶèĢħ
    0.14
    èªįçĤº
    0.14
    Activations Density 0.069%

    No Known Activations