© 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. 51122
    Prev
    Next
    INDEX
    Explanations

    emotional impact or feeling

    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
    æĬ±
    -0.11
    çģ¿çĥĤ
    -0.11
    æı©
    -0.10
    çµ®
    -0.08
    欣
    -0.08
    äºļè¿IJ
    -0.08
    åĶ¾
    -0.08
    éĥ¢
    -0.08
    arat
    -0.08
    æĬ±çĿĢ
    -0.08
    POSITIVE LOGITS
    æĦŁè§¦
    0.14
    æ·±åĪ»çļĦ
    0.13
    éľĩæĴ¼
    0.13
    æĦŁ
    0.12
    éľĩåĬ¨
    0.12
    æ·±åĪ»
    0.12
    å¾Īæ·±
    0.11
    åį°è±¡
    0.11
    åį°è±¡æ·±åĪ»
    0.11
    人å¿ĥ
    0.11
    Activations Density 0.042%

    No Known Activations