© 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. 62553
    Prev
    Next
    INDEX
    Explanations

    religious buildings

    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
    åĵij
    -0.12
    被åĬ¨
    -0.10
    家å±ħ
    -0.10
    éĢļè¡Įè¯ģ
    -0.09
    inka
    -0.08
    -headed
    -0.08
    磮
    -0.08
    illes
    -0.08
    izen
    -0.08
    ahl
    -0.08
    POSITIVE LOGITS
    æ±Ĺ
    0.09
    æĥħæĻ¯
    0.09
    æīĭèĩĤ
    0.09
    æĴŃç§į
    0.08
    åĨĻåŃĹ楼
    0.08
    æ·ĸ
    0.08
    æ¯ĶèµĽä¸Ń
    0.08
    èݪ
    0.08
    涵
    0.08
    æ°ijåĽ½
    0.08
    Activations Density 0.013%

    No Known Activations