© 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. 2113
    Prev
    Next
    INDEX
    Explanations

    household appliances and fixtures

    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
    第ä¸Ģ家
    -0.10
    ArrayOf
    -0.09
    åĴĮæĶ¯æĮģ
    -0.09
    èļĢ
    -0.09
    çºł
    -0.09
    æ¸ħåĩī
    -0.09
    æĻºèĥ½æīĭæľº
    -0.09
    ä¼IJ
    -0.09
     Fraser
    -0.08
    åĪ®
    -0.08
    POSITIVE LOGITS
    inqu
    0.08
    éĻ©
    0.08
     trunk
    0.08
     Colleg
    0.08
    æķħ乡
    0.08
     paran
    0.08
     Hok
    0.07
     há»ıng
    0.07
    tap
    0.07
    porno
    0.07
    Activations Density 0.053%

    No Known Activations