© 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. 60863
    Prev
    Next
    INDEX
    Explanations

    wedding

    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
    ively
    -0.13
    ities
    -0.12
    ément
    -0.10
    çķı
    -0.10
    baugh
    -0.10
    sing
    -0.09
     лиÑĨа
    -0.09
    ä¸ĥæĺŁ
    -0.09
    è¾ĺ
    -0.09
    levance
    -0.09
    POSITIVE LOGITS
    nesday
    0.10
    dings
    0.10
    ded
    0.09
    ç°ª
    0.09
    åīįå¤ķ
    0.09
    çŃĸåĪĴ
    0.09
    stral
    0.08
    zik
    0.08
    اÙħÙĦ
    0.08
    tk
    0.08
    Activations Density 0.010%

    No Known Activations