© 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. 34386
    Prev
    Next
    INDEX
    Explanations

    engagement and related words

    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
    æľįä»İ
    -0.10
    äºĮåįģäºĶ
    -0.09
    çŁ¥å·±
    -0.09
     tagName
    -0.08
    isten
    -0.08
    RefCount
    -0.08
    æĽĿåħī
    -0.08
    IME
    -0.08
    ruz
    -0.08
    zelf
    -0.08
    POSITIVE LOGITS
    è°ĥåĬ¨
    0.10
    æķ´ä¸ª
    0.09
    anium
    0.08
    Decl
    0.08
    æ¿Ģåıij
    0.08
    _declaration
    0.08
    æĥ³æī¾
    0.08
    æİĸ
    0.08
    elter
    0.08
    æĸĹ
    0.08
    Activations Density 0.017%

    No Known Activations