© 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. 60931
    Prev
    Next
    INDEX
    Explanations

    governors' surnames

    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
    éĶĦ
    -0.10
    mö
    -0.10
    ä¸ĢèĤ¡
    -0.09
    antor
    -0.09
    æŀ¢
    -0.09
    ä¸Ģ件äºĭæĥħ
    -0.09
    çĶ
    -0.09
    olis
    -0.08
    俪
    -0.08
    çĸ²åĬ³
    -0.08
    POSITIVE LOGITS
    ä¸į容
    0.11
    é¾Ľ
    0.10
    贪婪
    0.09
    yah
    0.09
    åĨįå¤ļ
    0.08
    ìĸ¼
    0.08
    oyo
    0.08
    exus
    0.08
    ãģĹãĤĩãģĨ
    0.08
    quee
    0.08
    Activations Density 0.003%

    No Known Activations