© 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. 18314
    Prev
    Next
    INDEX
    Explanations

    inspiring or inspirational words

    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¸ĢæĶ¯
    -0.09
    ä¸ĢéĹ´
    -0.09
    涩
    -0.09
     ÑģовеÑĢÑĪен
    -0.09
    æĮĩåįĹ
    -0.09
    elin
    -0.08
    ä»Ģä¹Īæł·çļĦ
    -0.08
    ä¸Ģåıª
    -0.08
    ä¸Ģé¢Ĺ
    -0.08
    è¯ķéªĮåĮº
    -0.08
    POSITIVE LOGITS
    visa
    0.10
    rup
    0.10
    ÑĢод
    0.09
    ÑĢоÑģÑĤ
    0.09
    éªł
    0.09
    éºŁ
    0.09
    å¥ĭæĸĹ
    0.09
    ssel
    0.09
    åĬ±å¿Ĺ
    0.08
    Ñĩки
    0.08
    Activations Density 0.008%

    No Known Activations