© 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. 11328
    Prev
    Next
    INDEX
    Explanations

    cheer or cheers

    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
    ional
    -0.13
    ted
    -0.10
    èµ°å»Ĭ
    -0.10
    rait
    -0.10
    ãģªãĤĬ
    -0.10
    ively
    -0.10
     sce
    -0.09
    ting
    -0.09
    èĽĭ
    -0.09
    ual
    -0.09
    POSITIVE LOGITS
    æĽĻåħī
    0.11
     chắn
    0.11
    icles
    0.10
    otes
    0.10
    é¼ĵèĪŀ
    0.09
    亮丽
    0.09
    itable
    0.09
    æĺİæľĹ
    0.09
    ouse
    0.09
    antro
    0.09
    Activations Density 0.010%

    No Known Activations