© 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. 5883
    Prev
    Next
    INDEX
    Explanations

    video game characters

    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
    æĺİæĹ¥
    -0.10
     нед
    -0.10
    isl
    -0.09
    indle
    -0.09
    æĺİ天
    -0.09
    鸾
    -0.09
    CAF
    -0.09
    æĪıåī§
    -0.08
    æł·çļĦ
    -0.08
    æ¹ĸåĮº
    -0.08
    POSITIVE LOGITS
    веÑģÑĤ
    0.10
    éĦľ
    0.09
    ä¸įæŃ»
    0.08
    CADE
    0.08
    åĪĿ次
    0.08
    wich
    0.08
     Gio
    0.08
    æĪĴ
    0.08
    åĶ¤
    0.08
    å·´æĭī
    0.08
    Activations Density 0.009%

    No Known Activations