© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8678
    Prev
    Next
    INDEX
    Explanations

    product features

    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
    dent
    -0.08
    个人信æģ¯
    -0.08
    å¼Ħ
    -0.08
    æĤ²è§Ĥ
    -0.07
    伺
    -0.07
    è¾¾æłĩ
    -0.07
    å°ļ
    -0.07
    uell
    -0.07
    stock
    -0.07
    çľĭä¸įæĩĤ
    -0.07
    POSITIVE LOGITS
     Ease
    0.09
    ä¸ĸçķĮä¸ĬæľĢ
    0.09
    æĹĹèĪ°
    0.09
     ÐĺгÑĢ
    0.09
    大å¹ħæıIJåįĩ
    0.09
    ease
    0.09
    å¥ijåIJĪ
    0.09
    _ENTER
    0.09
    åĩŃåĢŁ
    0.09
    åħ¨çIJĥ
    0.08
    Activations Density 0.094%

    No Known Activations