© 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. 18347
    Prev
    Next
    INDEX
    Explanations

    time-consuming

    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
    æĪIJçĨŁçļĦ
    -0.11
    å·²ä¹ħçļĦ
    -0.10
    èĨı
    -0.10
    çļĦ人çĶŁ
    -0.10
    åľ¨åĨħçļĦ
    -0.09
    é£ŀæī¬
    -0.09
    çļĦ身ä½ĵ
    -0.09
    atas
    -0.09
    çļĦçĥŃæĥħ
    -0.09
    éĩįè¦ģæĦıä¹ī
    -0.09
    POSITIVE LOGITS
    缸å½ĵ
    0.10
     ÙĦÙĦغاÙĬØ©
    0.10
    alcon
    0.09
    fully
    0.09
     enough
    0.09
    eworthy
    0.09
    æľīä¸Ģå®ļçļĦ
    0.09
    绾
    0.08
    å¯Ŀ
    0.08
    less
    0.08
    Activations Density 0.180%

    No Known Activations