© 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. 52884
    Prev
    Next
    INDEX
    Explanations

    one of the

    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
    ucc
    -0.09
    稳
    -0.09
    åģļçļĦäºĭæĥħ
    -0.09
    alten
    -0.08
    çĽijäºĭä¼ļ
    -0.08
     Shea
    -0.08
    åºķ
    -0.08
     supervised
    -0.08
    .googleapis
    -0.08
     MAGIC
    -0.07
    POSITIVE LOGITS
    è¿ĺ好
    0.15
    åĽºçĦ¶
    0.14
    ç½¢äºĨ
    0.11
    orsch
    0.10
    ãģĤãĤĬãģ¾ãģĻãģĮ
    0.10
    ä½Ĩä¸įéĻIJäºİ
    0.10
     thôi
    0.10
    ä¹ĭä½Ļ
    0.09
     ìŀĪì§Ģë§Į
    0.09
    çļĦåIJĮæŶ
    0.09
    Activations Density 0.039%

    No Known Activations