© 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. 61003
    Prev
    Next
    INDEX
    Explanations

    queensland and australian sports teams

    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
    éķ
    -0.08
    åįĥä¸ĩ
    -0.08
    å¿ĥçģµ
    -0.08
    æĺŁåħī
    -0.08
     presume
    -0.08
    å®ŀè´¨æĢ§
    -0.08
    icient
    -0.08
     Tud
    -0.07
    楯
    -0.07
    é£İåħī
    -0.07
    POSITIVE LOGITS
    PELL
    0.10
    ç½¢
    0.09
    modx
    0.09
    åĽ´è§Ĥ
    0.09
    hower
    0.09
    çIJī
    0.08
    erville
    0.08
    IPS
    0.08
    ı
    0.08
     Airways
    0.08
    Activations Density 0.007%

    No Known Activations