© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57464
    Prev
    Next
    INDEX
    Explanations

    birds and bird-related terms

    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
    æ½ľ
    -0.09
    æ½ľèīĩ
    -0.08
    æĻĥ
    -0.08
    èĺij
    -0.08
    ÐľÐŀ
    -0.08
    oust
    -0.08
     CAMERA
    -0.08
    æĦ
    -0.08
    upp
    -0.08
     Elf
    -0.08
    POSITIVE LOGITS
    鸣
    0.18
    鸣类
    0.18
     birds
    0.18
     Birds
    0.17
     bird
    0.17
    é³¥
    0.16
    Bird
    0.15
    ç¾½æ¯Ľ
    0.15
    å°ı鸣
    0.15
    åķĦ
    0.15
    Activations Density 0.088%

    No Known Activations