© 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. 32026
    Prev
    Next
    INDEX
    Explanations

    browser issues or settings

    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
    åĭĺæŁ¥
    -0.10
    leton
    -0.10
    模仿
    -0.10
    éĿĸ
    -0.10
    çĽ
    -0.10
    endet
    -0.10
    -live
    -0.09
    osphere
    -0.09
    æľīæľºä¼ļ
    -0.09
    .chk
    -0.09
    POSITIVE LOGITS
     intrinsic
    0.09
    è¿Ļä½į
    0.08
    ÑıÑħ
    0.08
    èĦ±
    0.08
    èµ·äºĨ
    0.08
    yh
    0.07
    um
    0.07
    å½ĵåľ°æĶ¿åºľ
    0.07
    认åIJĮ
    0.07
    enge
    0.07
    Activations Density 0.006%

    No Known Activations