© 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. 61292
    Prev
    Next
    INDEX
    Explanations

    verbs ending in -ing

    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
    sis
    -0.11
    å¸Ĥåľºä»½é¢Ŀ
    -0.10
    ãĤĤãģ®ãģ§ãģĻ
    -0.10
    åľ¨åħ¶
    -0.10
    ons
    -0.10
    åĩ³
    -0.09
    mis
    -0.09
    å®ŀå®ŀåľ¨åľ¨
    -0.09
    andal
    -0.09
    åĩłçĤ¹
    -0.09
    POSITIVE LOGITS
    缸ç»ĵåIJĪ
    0.10
    大åŀĭ
    0.10
    åIJĮä¸Ģ个
    0.10
    åIJİçļĦ
    0.09
    aka
    0.09
    æķ´ä¸ª
    0.09
    åIJĮä¸Ģ
    0.08
    æĸ°æĹ¶æľŁ
    0.08
    6
    0.08
    è¿ĩçļĦ
    0.08
    Activations Density 0.214%

    No Known Activations