© 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. 8536
    Prev
    Next
    INDEX
    Explanations

    ther/there and other common word endings

    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¸Ŀè·¯
    -0.09
    ole
    -0.08
     Salvador
    -0.08
     bá»ģn
    -0.08
    è·
    -0.08
     Sal
    -0.08
    è¿Ħä»Ĭ
    -0.08
    PED
    -0.08
    Salvar
    -0.08
    æķij人
    -0.07
    POSITIVE LOGITS
    inkle
    0.10
     Cousins
    0.09
    Ñĥг
    0.09
    ×ĸ׼
    0.09
    åIJijä¸Ĭ
    0.09
    åĬŃ
    0.09
     yönelik
    0.09
    ç¼Ģ
    0.09
    /gallery
    0.08
    æŁıæŀĹ
    0.08
    Activations Density 0.012%

    No Known Activations