© 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. 58037
    Prev
    Next
    INDEX
    Explanations

    orchestra names

    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
    ogl
    -0.08
    æŃ£è§Ħ
    -0.07
    é¼ĵ
    -0.07
    ÙĩÙĪ
    -0.07
    éĭª
    -0.07
    次ä¼ļè®®
    -0.07
    comed
    -0.07
    ä½ĵèĤ²
    -0.07
    è¡ħ
    -0.07
     coun
    -0.07
    POSITIVE LOGITS
    æ¼Ķç»İ
    0.12
    åı¦ä¸ĢåįĬ
    0.10
    ALAR
    0.10
    æĶ¾åģĩ
    0.10
    çĶľç¾İ
    0.10
    带åĬ¨
    0.10
    ç¹ģå¿Ļ
    0.10
    缸
    0.09
    æ¯ı次éĥ½
    0.09
    çļĦéĩį大
    0.09
    Activations Density 0.054%

    No Known Activations