© 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. 8178
    Prev
    Next
    INDEX
    Explanations

    license and copyright information

    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
    è´¨éĩıåĴĮ
    -0.17
    ç»ıéªĮåĴĮ
    -0.16
    ä¼ģä¸ļåĴĮ
    -0.16
    æŶéĹ´åĴĮ
    -0.15
    èĥ½åĬĽåĴĮ
    -0.15
    çIJĨ解åĴĮ
    -0.13
    管çIJĨåĴĮ
    -0.13
    建设åĴĮ
    -0.13
    æĬĢæľ¯åĴĮ
    -0.12
    æĸĩåĮĸåĴĮ
    -0.12
    POSITIVE LOGITS
    /or
    0.18
    /OR
    0.13
    缸ç»ĵåIJĪ
    0.12
    /etc
    0.12
     alike
    0.12
    åıĮéĩį
    0.11
    çŃīå·¥ä½ľ
    0.10
    çŃīæĸ¹éĿ¢
    0.10
    éĥ½éĿŀ常
    0.10
    çŃīæĸ¹å¼ı
    0.09
    Activations Density 1.644%

    No Known Activations