© 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. 32003
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
    liner
    -0.09
    ammer
    -0.08
    numer
    -0.07
    åĢ«
    -0.07
    家éĥ½çŁ¥éģĵ
    -0.07
     Rab
    -0.07
    å´Ĩ
    -0.07
     techn
    -0.07
    sj
    -0.06
    _SCOPE
    -0.06
    POSITIVE LOGITS
    éĩĬ
    0.11
    é«ĺ级
    0.11
    è¿Ļ个è¯į
    0.10
    ÅĽli
    0.10
    ä¸įæŃ»
    0.09
    åIJ«ä¹ī
    0.09
    æ±īè¯Ń
    0.09
    ä¾ĭ
    0.09
    å¼ķ
    0.09
    æĦıæĢĿ
    0.09
    Activations Density 0.158%

    No Known Activations