© 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. 31169
    Prev
    Next
    INDEX
    Explanations

    return trip back home

    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
    å´©
    -0.10
    åĪ¤
    -0.10
    è¿Ļ家ä¼Ļ
    -0.09
    æĪ¿éĹ´éĩĮ
    -0.09
    è¿Ľåľº
    -0.09
     ÑĦоÑĢ
    -0.09
    åħµåĻ¨
    -0.09
    STA
    -0.09
    è¿Ļåıª
    -0.09
    å®ĥåı¯ä»¥
    -0.09
    POSITIVE LOGITS
    åĽŀåĪ°
    0.12
    åĽŀä¾Ĩ
    0.11
    带åĽŀ
    0.11
    è¿Ķ
    0.11
    帰
    0.10
    åĽŀåĽ½
    0.10
    ä¸ĩ亿
    0.10
    åĽŀ家
    0.10
    åĽŀæĿ¥
    0.10
    åĽŀåİ»
    0.09
    Activations Density 0.038%

    No Known Activations