© 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. 34190
    Prev
    Next
    INDEX
    Explanations

    to the point where

    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
    ufs
    -0.09
    phil
    -0.09
    odu
    -0.09
    è§Ħ模æľĢ大
    -0.08
    两ä¸ī
    -0.08
     найд
    -0.08
    没éĹ®é¢ĺ
    -0.08
    åŁºåĩĨ
    -0.08
    åĨ¶çĤ¼
    -0.08
    åĸı
    -0.08
    POSITIVE LOGITS
    以èĩ³äºİ
    0.22
    以èĩ´
    0.18
    使ä¹ĭ
    0.12
    使å¾Ĺ
    0.11
    æĪIJ为äºĨ
    0.10
    èĩ´ä½¿
    0.10
    人次
    0.10
    使åħ¶
    0.09
     Lomb
    0.09
    èĩ³æĸ¼
    0.09
    Activations Density 0.042%

    No Known Activations