© 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. 37939
    Prev
    Next
    INDEX
    Explanations

    omnipresent, omniscient, Almighty

    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
    档次
    -0.11
    irl
    -0.10
    æĶ»åĬ¿
    -0.10
    çªĪ
    -0.09
    龸çİĭ
    -0.08
    à¹Ĥà¸Ļ
    -0.08
    gles
    -0.08
    matter
    -0.08
    ä¸įåIJ«
    -0.08
    brook
    -0.08
    POSITIVE LOGITS
    nel
    0.10
    ingly
    0.10
    èĢħçļĦ
    0.10
    æĭĸ
    0.09
    çŃ¹å¤ĩ
    0.09
    äºĭ
    0.09
    æ»ŀ
    0.09
     meanwhile
    0.09
    ELY
    0.09
    ork
    0.08
    Activations Density 0.011%

    No Known Activations