© 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. 1702
    Prev
    Next
    INDEX
    Explanations

    worsened by

    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
    è¦ģä¹Ī
    -0.11
    å©Ĩ
    -0.09
     Ness
    -0.09
    çĶŁæ¶¯
    -0.09
    æĭĤ
    -0.09
    æĽ´èĥ½
    -0.09
    å«Į
    -0.09
    зов
    -0.09
    ä¸įä¸Ģå®ļ
    -0.09
    åŃº
    -0.09
    POSITIVE LOGITS
    è¿ĺæľīä¸Ģ个
    0.10
    iley
    0.09
    è¿ĺæľī
    0.09
    è¿ĺè¦ģ
    0.09
    è¾ħ
    0.09
    è¿ĺå¾Ĺ
    0.09
    ipo
    0.09
    æľī个
    0.08
    è¿ĺæľīä¸ĢäºĽ
    0.08
    illos
    0.08
    Activations Density 0.068%

    No Known Activations