© 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. 5766
    Prev
    Next
    INDEX
    Explanations

    slowly lifted, softly :

    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
    第äºĮ天
    -0.10
    è¿ĺæľīä»Ģä¹Ī
    -0.09
    好好
    -0.09
     bè
    -0.09
    æĮĤåľ¨
    -0.09
    æĺ¯å¤ļä¹Ī
    -0.09
    PropertyParams
    -0.09
    defs
    -0.09
    å®Ĺ
    -0.09
    该æĢİä¹ĪåĬŀ
    -0.09
    POSITIVE LOGITS
    æĺ±
    0.09
    çħľ
    0.09
    iges
    0.08
    ØŃÙĨ
    0.08
    åIJĮæł·çļĦ
    0.07
    缸åIJĮçļĦ
    0.07
    缴è¾ĸå¸Ĥ
    0.07
    -navbar
    0.07
    主åĬ¨
    0.07
    çľĭ书
    0.07
    Activations Density 0.036%

    No Known Activations