© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7018
    Prev
    Next
    INDEX
    Explanations

    relative pronouns and conjunctions

    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
    -0.11
    èĥ½åĬĽåĴĮ
    -0.11
    ä¼ģä¸ļåĴĮ
    -0.11
    æĬĢæľ¯åĴĮ
    -0.10
    æĪĸèĢħ说
    -0.10
    å¾Ĺèµ·
    -0.09
    pak
    -0.09
    ç»ıéªĮåĴĮ
    -0.09
    æĸĩåĮĸåĴĮ
    -0.09
    ä¸İåħ¶
    -0.09
    POSITIVE LOGITS
    åIJİèĢħ
    0.18
    两èĢħ
    0.15
    äºĮèĢħ
    0.15
     latter
    0.14
     alike
    0.13
    éĥ½ä¸įæĺ¯
    0.13
    è¿ĻäºĽéĥ½æĺ¯
    0.13
    éĥ½æĺ¯éĿŀ常
    0.12
    ãģ©ãģ¡ãĤī
    0.12
    åīįèĢħ
    0.11
    Activations Density 0.507%

    No Known Activations