© 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. 3274
    Prev
    Next
    INDEX
    Explanations

    delivery and delivery-related 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
    æ³ī
    -0.10
    æ³īæ°´
    -0.09
    伪
    -0.09
    天åłĤ
    -0.09
    cro
    -0.09
    åIJŀ
    -0.09
    åĽ½äºº
    -0.09
    è¯Ī
    -0.08
     Needle
    -0.08
    TRS
    -0.08
    POSITIVE LOGITS
     deliveries
    0.22
     delivery
    0.22
    éħįéĢģ
    0.21
     Delivery
    0.20
    éĢģè´§
    0.20
    delivery
    0.19
     deliver
    0.18
    éĢģè¾¾
    0.18
    ä¸ĬéŨ
    0.17
     delivering
    0.17
    Activations Density 0.101%

    No Known Activations