© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35759
    Prev
    Next
    INDEX
    Explanations

    mission work and church organizations

    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
    .php
    -0.09
     PHP
    -0.09
    次
    -0.09
    沸èħ¾
    -0.09
     Catholic
    -0.09
    php
    -0.08
    _cast
    -0.08
    ifix
    -0.08
    家
    -0.08
    PHP
    -0.08
    POSITIVE LOGITS
    èģĮä¸ļæĬĢæľ¯
    0.10
    踢
    0.09
    اص
    0.09
     поÑĤеÑĢÑı
    0.09
    äºĨä¸Ģåı¥
    0.09
    _mr
    0.08
    .gwt
    0.08
    tement
    0.08
    åĹ
    0.08
    Ñıн
    0.08
    Activations Density 0.070%

    No Known Activations