© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19567
    Prev
    Next
    INDEX
    Explanations

    the fact that

    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
    ä¹Łå°±æĺ¯
    -0.10
    鬼
    -0.10
    -src
    -0.10
    æѧ
    -0.10
    åħ¶å®ŀå°±æĺ¯
    -0.09
    åĩºä¼ļ
    -0.09
    éĶŁ
    -0.09
    FieldName
    -0.09
    doch
    -0.09
    ãģ©ãģĵãĤį
    -0.08
    POSITIVE LOGITS
     fact
    0.18
     bahwa
    0.14
    fact
    0.13
     rằng
    0.13
    _fact
    0.12
    Fact
    0.12
     Fact
    0.11
    onte
    0.10
     Ø£ÙĨÙĩا
    0.10
    çļĦäºĭå®ŀ
    0.10
    Activations Density 0.205%

    No Known Activations