© 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. 8441
    Prev
    Next
    INDEX
    Explanations

    vehicles and systems

    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
     cars
    -0.09
    _ble
    -0.09
    skin
    -0.08
    alli
    -0.08
     doctr
    -0.08
    æĢ¨
    -0.08
    itters
    -0.08
    楼ä¸Ĭ
    -0.08
    lick
    -0.08
    Opaque
    -0.08
    POSITIVE LOGITS
    åĮ£
    0.12
    åħ¨çº¿
    0.10
    èİĽ
    0.09
    é¦ĸéĢī
    0.09
    éĺħ读åħ¨æĸĩ
    0.09
    æĶ¶è´¹ç«Ļ
    0.09
    annel
    0.09
    åľ¨äº¬
    0.09
    é¦ĸè½®
    0.09
    Ñĥв
    0.08
    Activations Density 0.327%

    No Known Activations