© 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. 4614
    Prev
    Next
    INDEX
    Explanations

    affirmations and evaluations

    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
    æł¼å¤ĸ
    -0.09
    åħ¥åĽŃ
    -0.08
    ä¸įåıĹ
    -0.08
    ä¸ĢæĿ¡é¾Ļ
    -0.08
    çŁĽçĽ¾
    -0.08
    åİ¢
    -0.08
    èĽĨ
    -0.08
     Truth
    -0.08
    æĹłåģ¿
    -0.08
    æ´¼
    -0.08
    POSITIVE LOGITS
    è°ħ解
    0.10
    amel
    0.10
    engo
    0.09
    à¸ģารà¸Ĺำà¸ĩาà¸Ļ
    0.09
    没éĹ®é¢ĺ
    0.09
    ossal
    0.09
    大家éĥ½åľ¨
    0.09
    NewItem
    0.09
    .communic
    0.08
    æĪijå°±
    0.08
    Activations Density 0.070%

    No Known Activations