© 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. 29390
    Prev
    Next
    INDEX
    Explanations

    de facto, ad hoc

    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
    arium
    -0.10
    mith
    -0.09
    oretical
    -0.08
     Äijẩy
    -0.08
    oud
    -0.08
    joy
    -0.08
    dock
    -0.08
    orthy
    -0.08
    paren
    -0.08
    Ñĭ
    -0.08
    POSITIVE LOGITS
    éĺ²æ°´
    0.10
    èĤª
    0.09
    人çĶŁçļĦ
    0.09
    å²ģçļĦ
    0.09
    éĿĸ
    0.09
    WARDS
    0.09
    ï¸ı
    0.09
    åķĦ
    0.09
    æľįåĬ¡åijĺ
    0.09
    峪
    0.09
    Activations Density 0.016%

    No Known Activations