© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37188
    Prev
    Next
    INDEX
    Explanations

    of choice

    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
    æ²±
    -0.10
    äºĶ大
    -0.10
    achi
    -0.10
    ä¸įæŃ»
    -0.10
    è°¥
    -0.10
    说æĪij
    -0.09
    ä¸įå½±åĵį
    -0.09
    /do
    -0.09
    ancel
    -0.09
    è¿ijè·Ŀ离
    -0.09
    POSITIVE LOGITS
     choice
    0.13
    é¦ĸéĢī
    0.12
    choice
    0.10
    Choice
    0.10
     choix
    0.09
    _choice
    0.09
     Choice
    0.09
    èĩ³ä¸Ĭ
    0.09
    çļĦéĢīæĭ©
    0.09
    apon
    0.09
    Activations Density 0.111%

    No Known Activations