© 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. 20816
    Prev
    Next
    INDEX
    Explanations

    even if, even when, even though

    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
     tháºŃm
    -0.12
    çĶļèĩ³è¿ĺ
    -0.12
    ç®Ģ缴
    -0.11
    çĶļèĩ³
    -0.11
    èĩªèº«çļĦ
    -0.10
    ç®Ģ缴æĺ¯
    -0.10
    åĩłä¹İæĺ¯
    -0.10
    è¦ģä¹Ī
    -0.10
    çĶļèĩ³æĺ¯
    -0.10
    ç®ĢçĽ´å°±æĺ¯
    -0.10
    POSITIVE LOGITS
    åľ¨å®¶éĩĮ
    0.11
    æľīäºĨ
    0.11
    æŶåĢĻ
    0.10
    theless
    0.10
    ÑģÑĤавка
    0.09
    æĥħåĨµä¸ĭ
    0.09
    åľ¨åħ¨çIJĥ
    0.09
    è¿ĻçĤ¹
    0.09
    è¿Ļ个æŶåĢĻ
    0.09
    å°ı游æĪı
    0.09
    Activations Density 0.024%

    No Known Activations