© 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. 16825
    Prev
    Next
    INDEX
    Explanations

    some, other, sometimes

    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
    éĬ®
    -0.09
    ächst
    -0.09
    âĢij
    -0.09
    _PD
    -0.09
    åĬ¿
    -0.08
    èµı
    -0.08
    WAYS
    -0.08
     ung
    -0.08
    herits
    -0.08
    Č
    -0.08
    POSITIVE LOGITS
    os
    0.09
     ÑģамоÑģÑĤоÑı
    0.08
    .curve
    0.08
    èħ°
    0.08
    ogie
    0.08
    лав
    0.08
    гÑĢан
    0.08
    çĦ¶æĺ¯
    0.08
    ÑĮÑİ
    0.08
    渴
    0.08
    Activations Density 0.053%

    No Known Activations