© 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. 39710
    Prev
    Next
    INDEX
    Explanations

    trademarks, copyrights, or legal notices

    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
    éĢĤåIJĪèĩªå·±
    -0.10
     contr
    -0.10
     Vimeo
    -0.10
    çŃ¾ä¸ĭ
    -0.09
    ниÑĨ
    -0.09
    è¿Ļ对
    -0.08
    æĤŃ
    -0.08
     Spice
    -0.08
    _contr
    -0.08
    渺
    -0.08
    POSITIVE LOGITS
    åĺ´
    0.10
    æģķ
    0.09
    æľīæĦı
    0.09
    yor
    0.09
     Joint
    0.09
    èĪĮ头
    0.08
    ä¸ĢéĹª
    0.08
     mouth
    0.08
    joint
    0.08
    æı¡
    0.08
    Activations Density 0.035%

    No Known Activations