© 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. 3132
    Prev
    Next
    INDEX
    Explanations

    a or an before word

    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
    iard
    -0.11
    ridden
    -0.10
    æľ¬äºĭ
    -0.10
    çijķ
    -0.09
    orting
    -0.09
    æħµ
    -0.09
    庸
    -0.09
    ä¼ı
    -0.09
    ibur
    -0.09
    åŃĹæł·
    -0.09
    POSITIVE LOGITS
     ones
    0.18
    ones
    0.13
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.10
    apor
    0.10
    .ones
    0.09
     Ones
    0.09
    åįķ车
    0.09
    ãĤĭãĤĤãģ®
    0.09
     yours
    0.09
    åIJij社ä¼ļ
    0.08
    Activations Density 0.158%

    No Known Activations