© 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. 37613
    Prev
    Next
    INDEX
    Explanations

    soldiers marching

    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
    赢家
    -0.09
    ãģĤãģª
    -0.08
    å®Ľ
    -0.08
    çĶŁèĤĸ
    -0.08
    综åIJĪæ²»çIJĨ
    -0.08
    ç»Ĩå¿ĥ
    -0.07
     Contents
    -0.07
    éĶ¦
    -0.07
    èľķåıĺ
    -0.07
    èķĪ
    -0.07
    POSITIVE LOGITS
    æķ´é½IJ
    0.10
    人åĿĩ
    0.10
    æĥĩ
    0.09
    roker
    0.09
    åĸĬ
    0.09
    è¿ij
    0.09
     marching
    0.09
    主è§Ĥ
    0.09
    è·ijæŃ¥
    0.09
    åīį沿
    0.08
    Activations Density 0.065%

    No Known Activations