© 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. 35290
    Prev
    Next
    INDEX
    Explanations

    delicacies, delight, delish

    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
    çķĭ
    -0.09
    åįĥéĩĮ
    -0.09
    æĽ´å¤ļä¿¡æģ¯
    -0.09
    è¿ĺéľĢ
    -0.09
    輩
    -0.08
    å·²æĺ¯
    -0.08
    appa
    -0.08
    èIJĮ
    -0.08
     fore
    -0.08
     Fore
    -0.08
    POSITIVE LOGITS
    两åıª
    0.11
    ä¼ģä¸ļæıIJä¾Ľ
    0.09
    ermen
    0.09
    å³Ń
    0.09
     pleading
    0.09
    è¿Ń
    0.09
    æĻ°
    0.08
    åĪ®
    0.08
    æ´½
    0.08
    ail
    0.08
    Activations Density 0.002%

    No Known Activations