© 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. 23189
    Prev
    Next
    INDEX
    Explanations

    restrictions and permissions

    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
    åĬł
    -0.09
    èĥĮåIJİçļĦ
    -0.08
    -END
    -0.08
    对æīĭ
    -0.08
    uddle
    -0.08
    ода
    -0.08
    ä¸Ģåij³
    -0.07
    udder
    -0.07
     Britann
    -0.07
    çļĦä¸ľè¥¿
    -0.07
    POSITIVE LOGITS
    æĺ¯ä¸Ģ件
    0.15
    æıŃ
    0.11
     done
    0.10
    åIJĦæł·
    0.10
    è¿Ļ件äºĭæĥħ
    0.10
    done
    0.10
    鸷
    0.10
    鬣
    0.09
    ä¹ĭ举
    0.09
    廿
    0.09
    Activations Density 0.314%

    No Known Activations