© 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. 21727
    Prev
    Next
    INDEX
    Explanations

    EU, Brexit, Association agreements

    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
    çĺł
    -0.11
    æķij人
    -0.09
    被æĬĵ
    -0.09
    鬣
    -0.08
    å§Ķ
    -0.08
     competition
    -0.08
     па
    -0.08
    éĺģ
    -0.08
    è¿Ļ个èģĮä¸ļ
    -0.08
    éĺ³
    -0.08
    POSITIVE LOGITS
    æ°ĶåĢĻ
    0.10
    IMATE
    0.09
    å®ŀè´¨æĢ§
    0.09
    桦
    0.09
    è¯ģåĪ¸äº¤æĺĵ
    0.08
    æ¾İ
    0.08
    ä¾ĥ
    0.08
    paging
    0.08
    伸
    0.08
    èѦ
    0.08
    Activations Density 0.063%

    No Known Activations