© 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. 18463
    Prev
    Next
    INDEX
    Explanations

    excellence award strategy services operations

    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
    åŃij
    -0.10
    éĻħ
    -0.09
    æ´½è°Ī
    -0.09
    æĪij羣çļĦ
    -0.08
    ç½ijåIJ§
    -0.08
    ä¸į认è¯Ĩ
    -0.08
    ç§ĭ
    -0.08
    å®ĮåĸĦçļĦ
    -0.08
    æIJĤ
    -0.08
     oc
    -0.08
    POSITIVE LOGITS
    _UNICODE
    0.09
    svc
    0.09
    顾客
    0.09
    ç²¾
    0.09
    .sess
    0.09
    ç¥ŀä»Ļ
    0.09
    å·¥èīº
    0.09
     defect
    0.09
    _refs
    0.08
    åĬ³
    0.08
    Activations Density 0.058%

    No Known Activations