© 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. 27592
    Prev
    Next
    INDEX
    Explanations

    express feelings

    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
    ä¾¿å®ľ
    -0.10
    严éĩįå½±åĵį
    -0.09
    uko
    -0.09
    严éĩį
    -0.09
    è²Įä¼¼
    -0.08
    被åĪ¤
    -0.08
    ulan
    -0.08
    ÑİÑīего
    -0.08
    大æ¦Ĥ
    -0.08
    bras
    -0.08
    POSITIVE LOGITS
    åħ´å¥ĭ
    0.13
    æ¿ĢåĬ¨
    0.12
    åĪļåĪļ
    0.10
    åģļ梦
    0.09
    æ¯ıä½į
    0.09
     excitement
    0.09
    è¿ĺæľīå¾Īå¤ļ
    0.09
    è¶ħé¢Ŀ
    0.09
    åħħå®ŀ
    0.09
    æĦŁåıĹåĪ°
    0.09
    Activations Density 0.147%

    No Known Activations