© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22023
    Prev
    Next
    INDEX
    Explanations

    days of the week

    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
    ÑģÑı
    -0.10
    çľ¼çIJĥ
    -0.09
    åľ¨è¿ĻéĩĮ
    -0.08
    治好
    -0.08
     USA
    -0.08
    æľĹ
    -0.08
     Tamb
    -0.08
    RFC
    -0.08
     Bradley
    -0.08
    壶
    -0.08
    POSITIVE LOGITS
    è¿ĺä¸įæĺ¯
    0.11
    ä¹¾åĿ¤
    0.10
    æľįåĬ¡æ°´å¹³
    0.09
    æ¦Ľ
    0.09
    imes
    0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    0.09
    uality
    0.09
    pest
    0.08
    åıijçĶŁçļĦ
    0.08
    ç¡®å®ŀæĺ¯
    0.08
    Activations Density 0.036%

    No Known Activations