© 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. 53792
    Prev
    Next
    INDEX
    Explanations

    incorporation and corporate acts

    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
    æĬĬå®ĥ
    -0.09
    iser
    -0.09
    åıij表äºĨ
    -0.09
     submissions
    -0.09
    çĶµåŃIJä¿¡æģ¯
    -0.08
    olta
    -0.08
    RIA
    -0.08
     Doming
    -0.08
    myfile
    -0.08
    æ¯ĶåĪ©
    -0.08
    POSITIVE LOGITS
     resc
    0.09
    åĿİåĿ·
    0.08
    èij£äºĭä¼ļ
    0.08
    åħ±å»º
    0.08
    _cn
    0.08
    acies
    0.08
    ä¸Ģè½®
    0.08
    æĿ¡ä¾ĭ
    0.08
    _CN
    0.08
    涵
    0.08
    Activations Density 0.121%

    No Known Activations