© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62512
    Prev
    Next
    INDEX
    Explanations

    assure, guarantee, insure that

    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
    èµĬ
    -0.10
    lightbox
    -0.09
    æĮ¹
    -0.09
    åºĵ
    -0.08
    æİı
    -0.08
    £¼
    -0.08
    æĸ°åĨłèĤºçĤİ
    -0.08
    é»ĺ
    -0.08
     trình
    -0.08
    edia
    -0.08
    POSITIVE LOGITS
    åģļåĪ°
    0.11
    AKE
    0.09
    è·¨çķĮ
    0.09
    fall
    0.09
    ç¡®ä¿Ŀ
    0.08
    arro
    0.08
    Ensure
    0.08
    åĪ°è´¦
    0.08
    éĺ²æ²»
    0.08
    èİĺ
    0.08
    Activations Density 0.039%

    No Known Activations