© 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. 27801
    Prev
    Next
    INDEX
    Explanations

    Panda and Pandas

    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
    åıijå±ķæ½ľåĬĽ
    -0.10
    åIJĦç§įåIJĦæł·
    -0.09
    kop
    -0.09
    æī©
    -0.08
    大大å°ıå°ı
    -0.08
    æľīèī²éĩijå±ŀ
    -0.08
    ä¸ĢåĪĨéĴ±
    -0.08
    æĨ¾
    -0.08
    .IT
    -0.08
    æĿŀ
    -0.08
    POSITIVE LOGITS
     Panda
    0.10
    -European
    0.09
     panda
    0.09
    缨
    0.09
    æģ¤
    0.09
    otle
    0.09
    æ»´æ»´
    0.09
    igure
    0.09
    èĥ¥
    0.09
    çĨĬçĮ«
    0.08
    Activations Density 0.007%

    No Known Activations