© 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. 22490
    Prev
    Next
    INDEX
    Explanations

    Surnames and proper nouns

    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
     пÑĢож
    -0.09
     swath
    -0.09
    ä¸Ģåı·
    -0.08
    èĻ
    -0.08
    åħ¥åľº
    -0.08
     conduct
    -0.08
    é©®
    -0.08
    æļ
    -0.08
    èIJ¥
    -0.08
    éĶī
    -0.08
    POSITIVE LOGITS
    çĵ¶åŃIJ
    0.10
    壶
    0.10
    æ³ī
    0.10
     negoci
    0.09
    çİ»
    0.09
    é¬ĺ
    0.09
    ÙĦÙĤ
    0.09
    -mf
    0.09
     bottles
    0.09
    æ³īæ°´
    0.09
    Activations Density 0.015%

    No Known Activations