© 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. 9679
    Prev
    Next
    INDEX
    Explanations

    inter-faith and religions

    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¸Ģ群
    -0.09
    åĥŃ
    -0.09
    åµĺ
    -0.09
    åªļ
    -0.09
    _weak
    -0.09
    樵
    -0.08
    à¸ķà¸ģ
    -0.08
    æīĵåĮħ
    -0.08
    NAL
    -0.08
    æĺ¯çĶ±
    -0.08
    POSITIVE LOGITS
     religions
    0.12
    å®ĹæķĻ
    0.11
    åıĮè¾¹
    0.09
    å¸Ľ
    0.09
     Religious
    0.09
    ä¼Ĭæĸ¯åħ°
    0.08
    zon
    0.08
     vas
    0.08
     Vas
    0.08
     religion
    0.08
    Activations Density 0.075%

    No Known Activations