© 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. 11908
    Prev
    Next
    INDEX
    Explanations

    game instances/dungeons

    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¿Ļ件
    -0.10
     Apparel
    -0.10
    秫
    -0.09
    èį·
    -0.09
     nerd
    -0.09
    getReference
    -0.08
    æī¼
    -0.08
    èĵĸ
    -0.08
    è£Ĩ
    -0.08
    çľ¼ç¥ŀ
    -0.08
    POSITIVE LOGITS
     Crown
    0.10
    ä»ĭ
    0.09
    对èĩªå·±
    0.09
    åĪ·
    0.09
    edriver
    0.09
    殿åłĤ
    0.09
    ENTA
    0.09
     closed
    0.08
    æł¹æį®ä¸įåIJĮ
    0.08
     crown
    0.08
    Activations Density 0.048%

    No Known Activations