© 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. 34716
    Prev
    Next
    INDEX
    Explanations

    popular television series

    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
     наÑĢ
    -0.09
    ologue
    -0.08
    ç§įç±»
    -0.08
    è¢Ī
    -0.08
    èģĶç½ij
    -0.08
    .ctrl
    -0.08
    横åIJij
    -0.08
    å«©
    -0.08
    ç»ı纪人
    -0.08
    çªŁ
    -0.08
    POSITIVE LOGITS
    ãģĤãģ®
    0.10
    å¨ģ
    0.10
    _checks
    0.09
    ÙħÙĪس
    0.09
    èijĹåIJį
    0.09
    åģī
    0.09
    erb
    0.09
    èĹIJ
    0.09
     popular
    0.09
    æºIJèĩª
    0.08
    Activations Density 0.241%

    No Known Activations