© 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. 29910
    Prev
    Next
    INDEX
    Explanations

    when we

    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
     ведÑĮ
    -0.09
    åĢŁæѤ
    -0.09
    åľ¨åĨħçļĦ
    -0.08
    .Pull
    -0.08
    vier
    -0.08
    Nib
    -0.08
    ä½Ĩä¸įéĻIJ
    -0.08
    .cloudflare
    -0.08
    .Caption
    -0.08
     nonetheless
    -0.08
    POSITIVE LOGITS
    çļĦæŶåĢĻ
    0.10
    æ´¥
    0.10
     _______,
    0.10
    éĩĩ访æŶ
    0.09
     ÙģØ¥ÙĨ
    0.09
    çļĦæĻĤåĢĻ
    0.09
    çݯå¢ĥåį«çĶŁ
    0.08
    æľīäºĨ
    0.08
    çļĦè¯Ŀ
    0.08
    è¦ģçĶ¨
    0.08
    Activations Density 0.232%

    No Known Activations