© 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. 11188
    Prev
    Next
    INDEX
    Explanations

    setting reminders and warnings

    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
    åĪ¶æľį
    -0.10
    .Entities
    -0.09
    èĶļ
    -0.09
    éģģ
    -0.09
    å§ĵ
    -0.09
    è¡Ķ
    -0.09
    çķħéĢļ
    -0.09
    èĮ¹
    -0.09
    人æµģ
    -0.08
    欢åij¼
    -0.08
    POSITIVE LOGITS
    æıIJéĨĴ
    0.38
     reminder
    0.26
    èѦåijĬ
    0.25
    èŃ¦ç¤º
    0.23
    æıIJ示
    0.23
     reminders
    0.23
     remind
    0.23
    reminder
    0.22
     reminding
    0.21
     warning
    0.21
    Activations Density 0.067%

    No Known Activations