© 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. 21701
    Prev
    Next
    INDEX
    Explanations

    bird, birder, birds, birding

    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
    游泳
    -0.11
    èĪĨ论
    -0.10
    æĦļ
    -0.09
    梦
    -0.08
    .FLAG
    -0.08
    OLUM
    -0.08
    æĬ±ä½ı
    -0.08
    代çIJĨ
    -0.08
    ä¸ī代
    -0.08
    kee
    -0.08
    POSITIVE LOGITS
     bird
    0.11
    é³¥
    0.10
    鸣类
    0.10
    鸣
    0.10
    ä¸ĵèģĮ
    0.09
     Bird
    0.09
    åħ¨æ°ij
    0.09
     зак
    0.09
    bird
    0.08
    æijĩ
    0.08
    Activations Density 0.095%

    No Known Activations