© 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. 16772
    Prev
    Next
    INDEX
    Explanations

    libraries and librarians

    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
    ement
    -0.11
    åĴĮå®ĮåĸĦ
    -0.10
    æĤłæĤł
    -0.09
    iment
    -0.09
    RIPT
    -0.09
    è°Ľ
    -0.09
    å¼Ĥ
    -0.09
    æĸĩåĮĸä¼łåªĴ
    -0.09
    .datas
    -0.09
    ä¸įäºĨ
    -0.08
    POSITIVE LOGITS
    onet
    0.09
    绪
    0.09
    åİŁæĸĩåľ°åĿĢ
    0.08
    yer
    0.08
    å·¥ä½ľäººåijĺ
    0.08
    æ³ķ人
    0.08
    çķĮ
    0.08
    èĮĤ
    0.08
    å·¥ä½ľæĬ¥åijĬ
    0.08
    ضع
    0.08
    Activations Density 0.012%

    No Known Activations