© 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. 27184
    Prev
    Next
    INDEX
    Explanations

    list item separators

    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
    çĭ¬ä¸ĢæĹłäºĮ
    -0.11
    åįģ足
    -0.10
    å½¹
    -0.10
    å½ĵåľ°äºº
    -0.10
    eneg
    -0.10
    .boost
    -0.09
    çĭ¬çī¹çļĦ
    -0.09
    åħīéĺ´
    -0.09
    å½ĵåľ°æĶ¿åºľ
    -0.09
    鬻
    -0.09
    POSITIVE LOGITS
    åħ¶æ¬¡æĺ¯
    0.09
     highest
    0.09
     other
    0.08
    é²ģ
    0.08
    ero
    0.08
    ä»ħ次äºİ
    0.08
    æĭľ
    0.08
    akk
    0.08
    åħ¶ä»ĸ
    0.08
     runner
    0.08
    Activations Density 0.068%

    No Known Activations