© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 64032
    Prev
    Next
    INDEX
    Explanations

    something or anything

    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
    Negative Logits
    éĢĹ
    -0.10
    æ¿Ģ
    -0.09
    çļĦä¸Ģ项
    -0.09
    å»īä»·
    -0.09
    åijĬè¯īæĪij
    -0.09
    éĩįè¦ģä½ľçĶ¨
    -0.09
    ibbon
    -0.09
    çļĦä¸Ģç§į
    -0.08
    ester
    -0.08
    poses
    -0.08
    POSITIVE LOGITS
    Äįe
    0.10
    çģ¿
    0.09
    çģ¿çĥĤ
    0.09
    åĩºæĿ¥äºĨ
    0.09
     Cul
    0.09
    æ±ľ
    0.08
    çłĶåıij
    0.08
     ÑģоÑħ
    0.08
    ä¸įåĩºæĿ¥
    0.08
    åĩºæĿ¥
    0.08
    Activations Density 0.247%

    No Known Activations