© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60689
    Prev
    Next
    INDEX
    Explanations

    who is/are/have/knows

    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
    Negative Logits
    å®ĥæĺ¯
    -0.09
    trag
    -0.09
    饵
    -0.09
    ucci
    -0.09
    豺
    -0.08
    èĤ¢
    -0.08
    fort
    -0.08
    è¿Ļåıª
    -0.08
    hä
    -0.08
    ucc
    -0.08
    POSITIVE LOGITS
    soever
    0.11
    acter
    0.10
    EVER
    0.10
    ÙĬا
    0.10
    ever
    0.09
    æīĵä»Ĺ
    0.09
    åħ¨åĽ½äººå¤§
    0.09
    ami
    0.09
    étude
    0.09
    RITE
    0.09
    Activations Density 0.039%

    No Known Activations