© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36569
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

    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
    hell
    -0.09
    æĪIJé¾Ļ
    -0.09
    æĿ²
    -0.09
    æľīæľŁ
    -0.09
    æĮīæŶ
    -0.09
    åľ¨è¿ĩ渡
    -0.08
    èµł
    -0.08
    ä»İå°ı
    -0.08
    à¹Ģหà¸Ļ
    -0.08
    éĢĤåIJĪèĩªå·±
    -0.08
    POSITIVE LOGITS
    tml
    0.09
    èĮĥ
    0.09
    vä
    0.09
    çıIJ
    0.08
    seudo
    0.08
    pdb
    0.08
    acent
    0.08
    hait
    0.08
    ippers
    0.08
    ีà¹ī
    0.08
    Activations Density 0.027%

    No Known Activations