© 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. 679
    Prev
    Next
    INDEX
    Explanations

    family members and relations

    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
    ÑĢÑıд
    -0.09
    tlement
    -0.09
    æݨè¡Į
    -0.09
    ìĤ¬ëĬĶ
    -0.09
    åį±å®³
    -0.08
    é«Ń
    -0.08
    大æĸ¹
    -0.08
    Ặ
    -0.08
    ENSION
    -0.08
    èĥ±
    -0.08
    POSITIVE LOGITS
    æĭľ
    0.09
    天çĶŁ
    0.09
    imon
    0.09
    å¼łå®¶
    0.09
    dit
    0.09
    åħ¬çº¦
    0.09
    檫
    0.08
    ohn
    0.08
     Anc
    0.08
    dek
    0.08
    Activations Density 0.002%

    No Known Activations