© 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. 17451
    Prev
    Next
    INDEX
    Explanations

    homogeneous / uniform species

    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
    æ³ī
    -0.10
    ä¸Ĭæ¦ľ
    -0.09
    æĮ¤
    -0.09
    è·»
    -0.09
    è°ĭ
    -0.09
    æŀĿ
    -0.09
    Suite
    -0.08
    andid
    -0.08
    åŃ¦ä¹łæĪIJ绩
    -0.08
    屿
    -0.08
    POSITIVE LOGITS
     monoc
    0.10
     hom
    0.10
     Äijá»ĵng
    0.09
    ä¸ĵ
    0.09
    åįķä¸Ģ
    0.09
     mon
    0.09
    åIJĮè¡Į
    0.09
    åĸī
    0.09
    åįķè°ĥ
    0.09
    ä¸ĵ注
    0.09
    Activations Density 0.132%

    No Known Activations