© 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. 8361
    Prev
    Next
    INDEX
    Explanations

    use and its applications

    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
    çıł
    -0.10
    éĥ¨åī¯
    -0.10
    第ä¸Ģ家
    -0.09
    为äºĨæĽ´å¥½
    -0.09
    æĢİèĥ½
    -0.09
    åı¯æĥ³
    -0.09
    èĨº
    -0.09
    çĵł
    -0.09
    æĢİä¹Īä¼ļ
    -0.09
    jak
    -0.08
    POSITIVE LOGITS
    è¿Ļç§įæĸ¹å¼ı
    0.14
    è¿Ļç§įæĸ¹æ³ķ
    0.13
    è¿Ļ段
    0.10
    çĶ¨äºİ
    0.09
    è¿Ļç§į
    0.09
    辩论
    0.09
    ILLE
    0.09
    è¿Ļé¦ĸ
    0.09
    æ¸Ĺ
    0.08
    emme
    0.08
    Activations Density 0.150%

    No Known Activations