© 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. 4600
    Prev
    Next
    INDEX
    Explanations

    polite requests and future 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
    ç»Ħç»ĩé¢Ĩ导
    -0.09
    ÙĬÙĪÙĨ
    -0.09
    ober
    -0.09
    è¿ĺå°Ĩ
    -0.09
    alytics
    -0.09
    onaut
    -0.09
    æݨèįIJéĺħ读
    -0.09
    åįĥéĩĮ
    -0.09
    ä¸ĵ家åѦèĢħ
    -0.08
    éĥ´
    -0.08
    POSITIVE LOGITS
     would
    0.26
    would
    0.25
     Would
    0.23
    Would
    0.22
     würde
    0.20
     serait
    0.18
     wouldn
    0.15
     serÃŃa
    0.15
     wäre
    0.14
     zou
    0.14
    Activations Density 0.255%

    No Known Activations