© 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. 19916
    Prev
    Next
    INDEX
    Explanations

    the accompanied by nouns

    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
    å¿ĥ仪
    -0.12
    å¿ĥ仪çļĦ
    -0.11
    æªĢ
    -0.10
    çļĦ人æĿ¥è¯´
    -0.10
    /her
    -0.09
    大åıij
    -0.09
     own
    -0.09
    åľ¨åĨħçļĦ
    -0.09
    å°±å¤ŁäºĨ
    -0.09
    éģĺ
    -0.08
    POSITIVE LOGITS
    è¿Ļä¹Łæĺ¯
    0.10
    æĢķ
    0.10
     mere
    0.10
    èĥ½åIJ¦
    0.09
    ä¹ŁåĽłæѤ
    0.08
    è¿Ļä¹Ł
    0.08
    çłĶ究表æĺİ
    0.08
    åĪ«
    0.08
    æĭħ
    0.08
     question
    0.08
    Activations Density 0.207%

    No Known Activations