© 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. 4998
    Prev
    Next
    INDEX
    Explanations

    plural nouns ending in 's'

    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
    oven
    -0.10
    ä»°
    -0.10
    ãģ£ãģ
    -0.10
    -aut
    -0.09
    èıĬèĬ±
    -0.09
    ä¸Ģ个个
    -0.09
    åı¦ä¸ĢåįĬ
    -0.09
    ANNER
    -0.09
    ÑĢаÑī
    -0.09
    icks
    -0.09
    POSITIVE LOGITS
    åIJİå¤ĩ
    0.08
    gon
    0.08
     Tan
    0.08
    äºı
    0.08
    .react
    0.07
    sn
    0.07
    runs
    0.07
    åıĭ们
    0.07
    ave
    0.07
    mos
    0.07
    Activations Density 0.043%

    No Known Activations