© 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. 5993
    Prev
    Next
    INDEX
    Explanations

    myriad of

    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
    san
    -0.09
    .raise
    -0.09
    arez
    -0.09
    asts
    -0.09
    ses
    -0.09
    Ñĩив
    -0.09
    åģļçļĦäºĭ
    -0.08
    ably
    -0.08
    roud
    -0.08
     *((
    -0.08
    POSITIVE LOGITS
    éħĬ
    0.11
    èĪ¬çļĦ
    0.10
     sclerosis
    0.10
    ä¹ĭ举
    0.10
    çļĦç¼ĺ
    0.10
    èĪ¬
    0.10
    åıªè§ģ
    0.09
    æݥ触åĪ°
    0.09
    -minded
    0.09
    ç¡IJ
    0.09
    Activations Density 0.006%

    No Known Activations