© 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. 48777
    Prev
    Next
    INDEX
    Explanations

    verbs ending in -ing

    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
    دÙĪÙĨ
    -0.09
    使人
    -0.09
    åķĬ
    -0.08
    æĢ§å¼º
    -0.08
    åĩij
    -0.08
    èĭ´
    -0.08
    泡
    -0.08
    .emit
    -0.08
     Alo
    -0.07
     nữa
    -0.07
    POSITIVE LOGITS
    èĭĩ
    0.10
    ç»ĵæŀĦæĢ§
    0.10
     некоÑĤоÑĢ
    0.10
    ä½ķ度ãĤĤ
    0.09
    åĩłæ¬¡
    0.09
    uka
    0.09
    ldr
    0.09
     Powered
    0.09
    ä¸Ģæīĭ
    0.09
    Ñĥма
    0.09
    Activations Density 0.074%

    No Known Activations