© 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. 22718
    Prev
    Next
    INDEX
    Explanations

    both and

    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
    åħ¶å®ŀå°±æĺ¯
    -0.10
     конеÑĩно
    -0.09
    å«£
    -0.09
     Authors
    -0.09
    _VO
    -0.08
    pressions
    -0.08
    é¨
    -0.08
    Ãły
    -0.08
    继ç»Ńä¿ĿæĮģ
    -0.08
     Bam
    -0.08
    POSITIVE LOGITS
    åIJĮæŶ
    0.19
    åħ¼é¡¾
    0.18
     both
    0.18
    both
    0.17
    åIJĮæĻĤ
    0.16
     lẫn
    0.16
     cả
    0.15
     simultaneously
    0.15
    çļĦåIJĮæŶ
    0.14
    åħ¼åħ·
    0.14
    Activations Density 0.317%

    No Known Activations