© 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. 23030
    Prev
    Next
    INDEX
    Explanations

    positive emotions or amusement

    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
    æģIJæĥ§
    -0.11
    ç»ĿæľĽ
    -0.10
    æĢµ
    -0.10
    黾
    -0.10
    æĤļ
    -0.10
    éķĽ
    -0.10
     Forg
    -0.10
    edList
    -0.10
    è¯ķçĿĢ
    -0.10
    å°¬
    -0.10
    POSITIVE LOGITS
    å¾ĹæĦı
    0.12
    èĥľåĪ©
    0.11
    çĥŁçģ«
    0.10
    享
    0.09
    åĺ´è§Ĵ
    0.09
    满足
    0.08
    å¼ĢèĬ±
    0.08
    çĭĤ
    0.08
    åħ´å¥ĭ
    0.08
     thrill
    0.08
    Activations Density 0.170%

    No Known Activations