© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9057
    Prev
    Next
    INDEX
    Explanations

    cultivars, cloning, selection, new varieties

    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
    ä¸į说
    -0.09
    æĭĮ
    -0.09
    æĺİæľĹ
    -0.08
    ertz
    -0.08
    沸èħ¾
    -0.08
    çĪĨ
    -0.08
    PerPage
    -0.08
    çŀ½
    -0.08
    fleet
    -0.07
    ç¥Ń
    -0.07
    POSITIVE LOGITS
    糧
    0.10
    èĪħ
    0.10
    åĩ¡
    0.10
    主æĮģ
    0.10
    antee
    0.09
    主æĮģ人
    0.09
    æİĪ
    0.09
    emin
    0.09
    _ipc
    0.09
     graft
    0.09
    Activations Density 0.050%

    No Known Activations