© 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. 31359
    Prev
    Next
    INDEX
    Explanations

    that followed by "the" or "half"

    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
    åĽłä¸ºä»ĸ们
    -0.11
    æĪij们认为
    -0.11
     _______,
    -0.11
    ìĹ°êµ¬
    -0.11
    åĽłä¸ºæĪij们
    -0.10
    çľ¼åīįçļĦ
    -0.10
    è¾ľ
    -0.10
    illion
    -0.10
    æĥ³è±¡
    -0.10
    æį®äºĨ解
    -0.10
    POSITIVE LOGITS
    ä¸įä½Ĩ
    0.09
    è¶Ĭæĺ¯
    0.09
    è¶Ĭ
    0.09
    0.09
    soever
    0.08
    åį³ä½¿
    0.08
    2
    0.08
    1
    0.08
    :↵
    0.08
    主è¦ģæľī
    0.08
    Activations Density 0.154%

    No Known Activations