© 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. 55982
    Prev
    Next
    INDEX
    Explanations

    celebrity names and scandals

    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
    åłµ
    -0.08
     Freder
    -0.08
    驱åĬ¨
    -0.08
    ìĥģìĿĦ
    -0.08
    iez
    -0.08
    åİ¿åŁŁ
    -0.08
    _examples
    -0.08
    ç»ĩ
    -0.08
    åĬ©åѦ
    -0.08
    æ°¨éħ¸
    -0.08
    POSITIVE LOGITS
    ä¼łåĩº
    0.09
    ernet
    0.09
    å¿«é¤IJ
    0.09
    黯
    0.09
    çĹ¿
    0.09
    å½¼æѤ
    0.09
    æķĪæŀľåĽ¾
    0.08
    åı¦ä¸ĢåįĬ
    0.08
    isman
    0.08
    åIJĪä½ľä¼Ļä¼´
    0.08
    Activations Density 0.036%

    No Known Activations