© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9406
    Prev
    Next
    INDEX
    Explanations

    glassware, cups, bottles, bowls

    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
     наÑĢ
    -0.12
    åĬ£
    -0.11
     иг
    -0.09
    é¢Ĺç²Ĵ
    -0.09
    çħİ
    -0.09
    åħ¨å±Ģ
    -0.09
    æ´¾
    -0.09
    å¤©çľŁ
    -0.09
    é¡Ĩ
    -0.09
    inha
    -0.08
    POSITIVE LOGITS
    UserCode
    0.09
    åĨµ
    0.08
    ç«Ļç«ĭ
    0.08
    æĸĩåĮĸéģĹ产
    0.08
    ervlet
    0.08
    çīĪæĿĥæīĢæľī
    0.08
    yro
    0.08
    itti
    0.08
    GAN
    0.08
    harma
    0.08
    Activations Density 0.036%

    No Known Activations