© 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. 3844
    Prev
    Next
    INDEX
    Explanations

    getting + adjective or gerund

    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
    为æŃ¢
    -0.10
    ned
    -0.09
    éĤ£ä¸Ģ天
    -0.09
    çļĦåľ°æŃ¥
    -0.09
     Trot
    -0.09
    åĭº
    -0.09
    веден
    -0.09
    ãģ¾ãģ¾
    -0.08
    uta
    -0.08
    éĻħ
    -0.08
    POSITIVE LOGITS
     rid
    0.10
    åĬŀ好
    0.09
    cord
    0.09
    alach
    0.08
    Backing
    0.08
    ionale
    0.08
    semblies
    0.08
    æİ¥è¿ij
    0.08
    rowData
    0.08
    ,application
    0.08
    Activations Density 0.035%

    No Known Activations