© 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. 54046
    Prev
    Next
    INDEX
    Explanations

    full moon

    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
    è´¿
    -0.10
     pros
    -0.10
    TED
    -0.10
    龸çİĭ
    -0.09
    èĬ¥
    -0.09
    åīįçŀ»æĢ§
    -0.09
    ä¸į让
    -0.09
    æıIJæĮ¯
    -0.08
    åĩĨåħ¥
    -0.08
    çŀł
    -0.08
    POSITIVE LOGITS
     moon
    0.13
     moons
    0.12
    æľĪ亮
    0.11
    æľĪ
    0.10
    çļİ
    0.10
     Moon
    0.10
    åľĨ满
    0.10
    æľĪåĪĿ
    0.10
    满
    0.09
    moon
    0.09
    Activations Density 0.041%

    No Known Activations