© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60565
    Prev
    Next
    INDEX
    Explanations

    landslide, flow, trail

    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
    Negative Logits
    åĸĻ
    -0.12
     duck
    -0.12
    èĢIJ
    -0.11
     ducks
    -0.11
     Duck
    -0.11
    é¸Ń
    -0.10
    olds
    -0.10
    é¹Į
    -0.09
    æĭIJ
    -0.09
    é³¥
    -0.09
    POSITIVE LOGITS
    ä»Ĺ
    0.10
    åłµå¡ŀ
    0.10
    å´©
    0.10
    æĮŁ
    0.09
    综åIJĪæ²»çIJĨ
    0.09
    å£ħ
    0.09
    Trail
    0.09
    ä»İæĿ¥ä¸į
    0.09
    çĸ¾
    0.08
    人为
    0.08
    Activations Density 0.035%

    No Known Activations