© 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. 51944
    Prev
    Next
    INDEX
    Explanations

    my dear child

    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
    ä¸ŃéĢĶ
    -0.10
    ãģ¦ãģĦ
    -0.09
    chas
    -0.09
    [model
    -0.08
    æ£ĭ
    -0.08
    çĶŁæľº
    -0.08
    为ä»Ģä¹Īä¸į
    -0.08
    inct
    -0.08
    sc
    -0.08
    ãħ¤
    -0.08
    POSITIVE LOGITS
    åĵī
    0.09
    çħ³
    0.09
    è¨Ģè¡Į
    0.09
    تاب
    0.09
    SCRIPT
    0.09
    éĹ¾
    0.09
     оÑĩеÑĢедÑĮ
    0.09
    éĢł
    0.08
    çįł
    0.08
    åIJİåį«
    0.08
    Activations Density 0.012%

    No Known Activations