© 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. 35194
    Prev
    Next
    INDEX
    Explanations

    level

    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
    åīįéĢĶ
    -0.11
     ÑģкаÑĩ
    -0.10
    먼
    -0.09
    éĥ¡
    -0.09
    çļĦéģĵçIJĨ
    -0.09
    æ¯Ķäºļ
    -0.09
    Scan
    -0.09
    åĺ´å·´
    -0.09
    çĶŁæĦı
    -0.09
    Earn
    -0.08
    POSITIVE LOGITS
    åºĶæľīçļĦ
    0.11
     recommended
    0.11
    åħ¬å¸ĥçļĦ
    0.10
    recommended
    0.10
    è§Ħå®ļçļĦ
    0.10
    çIJĨæĥ³çļĦ
    0.10
    建议
    0.10
    æݨèįIJ
    0.10
    æľīåħ³è§Ħå®ļ
    0.10
    æłĩåĩĨ
    0.10
    Activations Density 0.089%

    No Known Activations