© 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. 53576
    Prev
    Next
    INDEX
    Explanations

    power plants

    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
    é¢ĸ
    -0.10
    anko
    -0.10
    æİĴéĺŁ
    -0.10
    åĴĮæĬĢæľ¯
    -0.10
    æijĪ
    -0.09
    è¾ĺ
    -0.09
    æĽľ
    -0.09
    åĮħ袱
    -0.09
    ç§ĺ书éķ¿
    -0.09
    è°ľ
    -0.09
    POSITIVE LOGITS
    farm
    0.10
    åİĤ
    0.09
    TN
    0.08
    åıį转
    0.08
    ä¸įä¸Ĭ
    0.08
     Liver
    0.08
    arme
    0.08
    干线
    0.08
    .eclipse
    0.07
    jet
    0.07
    Activations Density 0.031%

    No Known Activations