© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38438
    Prev
    Next
    INDEX
    Explanations

    feelings about emotions and states

    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
    eer
    -0.10
    IMUM
    -0.09
    åIJĦåĮº
    -0.08
    aque
    -0.08
    åĬ¨éĿĻ
    -0.08
    عÙĬÙĨ
    -0.08
    unik
    -0.08
    edor
    -0.08
    åłª
    -0.08
    /update
    -0.08
    POSITIVE LOGITS
    ãģĸ
    0.10
    æģĭ
    0.09
    åľ°ä¸Ĭ
    0.09
    ä¸Ī夫
    0.09
    æľ¬ç½ijç«Ļ
    0.09
    æĦ«
    0.09
    craft
    0.09
    atical
    0.08
    otec
    0.08
    çļĦåĦ¿åŃIJ
    0.08
    Activations Density 0.005%

    No Known Activations