© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9338
    Prev
    Next
    INDEX
    Explanations

    contract and void contract

    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
    éĥ½å¸Ĥ
    -0.10
    èħĶ
    -0.10
    æĮĩåįĹ
    -0.10
    æľīèī²
    -0.09
    éķľ
    -0.09
    秽
    -0.09
     Erot
    -0.09
    erot
    -0.09
    sss
    -0.09
    åįķä¸Ģ
    -0.09
    POSITIVE LOGITS
    åIJĪåIJĮ
    0.14
    订
    0.12
    履约
    0.10
     contract
    0.10
    约å®ļ
    0.10
    为é¦ĸ
    0.10
     Contracts
    0.10
    -inv
    0.10
    个交æĺĵ
    0.09
    è¿Ŀ约
    0.09
    Activations Density 0.236%

    No Known Activations