© 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. 4244
    Prev
    Next
    INDEX
    Explanations

    related to feelings and actions

    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
    åIJĦä½į
    -0.11
    èĻ¹
    -0.09
    urgeon
    -0.09
    ä¸Ģç«Ļ
    -0.08
    ä¼Ĺå¤ļ
    -0.08
    对æłĩ
    -0.08
    .ga
    -0.08
    çķĻç»Ļ
    -0.08
    ['__
    -0.08
    ubit
    -0.08
    POSITIVE LOGITS
     themselves
    0.14
    ä¹ŁåIJĮæł·
    0.13
    åIJĮæł·çļĦ
    0.13
    è·Łä½ł
    0.13
    缸åIJĮ
    0.12
    åIJĦèĩª
    0.12
     ebenfalls
    0.11
    ä¹Łéĥ½
    0.11
    åIJĮ樣
    0.11
    åĪĨ享
    0.11
    Activations Density 0.113%

    No Known Activations