© 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. 50003
    Prev
    Next
    INDEX
    Explanations

    Churches and religious figures

    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
    çĽ¼
    -0.10
     brows
    -0.10
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.09
    æ·ij
    -0.09
    çī¹ä»·
    -0.09
    Streams
    -0.09
    Mix
    -0.09
    ä¸īåįĥ
    -0.08
    ä¸īç§į
    -0.08
     MIX
    -0.08
    POSITIVE LOGITS
    æĻŀ
    0.09
    plusplus
    0.08
    verage
    0.08
    éļ¶å±ŀäºİ
    0.08
    西æ´ĭ
    0.08
    åıĹåĪ°
    0.08
    o
    0.08
    æĪĺåıĭ
    0.08
    åĪ¶çº¦
    0.08
    åıĹåĪ°äºĨ
    0.08
    Activations Density 0.002%

    No Known Activations