© 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. 21664
    Prev
    Next
    INDEX
    Explanations

    opposed, competing, interacting relationships

    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
    PIC
    -0.10
    æ¥Ķ
    -0.10
    æį¡
    -0.09
    .mx
    -0.09
    .cent
    -0.09
     Exped
    -0.08
    nic
    -0.08
    æİı
    -0.08
    orange
    -0.08
    æĽ´å¤ļä¿¡æģ¯
    -0.08
    POSITIVE LOGITS
    å½¼æѤ
    0.14
    åľ¨ä¸Ģèµ·
    0.11
    äºĴ缸
    0.10
    两个
    0.10
     together
    0.10
     mutually
    0.10
     elkaar
    0.09
    èµ·æĿ¥äºĨ
    0.09
    ä¿©
    0.09
    缸äºĴ
    0.09
    Activations Density 0.332%

    No Known Activations