© 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. 37744
    Prev
    Next
    INDEX
    Explanations

    you can

    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
    äºĨä¸Ģåľº
    -0.10
    rne
    -0.09
    踵
    -0.09
    ä¸ĢéŨ
    -0.09
    åİĺ
    -0.09
    æijĩäºĨ
    -0.09
    æŁIJç§į
    -0.08
    ç£ħ
    -0.08
    åĬŀ好
    -0.08
    жа
    -0.08
    POSITIVE LOGITS
    åľ¨è¿ĻéĩĮ
    0.12
    è¿ĻéĩĮæĺ¯
    0.11
    ä»»ä½ķä¸Ģ个
    0.11
    ä¹Łåı¯ä»¥
    0.10
    ä¹ŁåºĶ该
    0.10
    è¿ĻéĩĮçļĦ
    0.10
    kü
    0.09
    è¿ĻéĩĮ
    0.09
     here
    0.09
    礼è²Į
    0.09
    Activations Density 0.202%

    No Known Activations