© 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. 937
    Prev
    Next
    INDEX
    Explanations

    an indefinite article followed by a noun

    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
    criptor
    -0.09
    ichel
    -0.09
    она
    -0.09
    ÑĤеÑĢ
    -0.09
    éĺ¿å§¨
    -0.09
    æĴ¼
    -0.09
    reich
    -0.09
    çī¹æľĹ
    -0.09
    akest
    -0.08
    ignon
    -0.08
    POSITIVE LOGITS
    诸å¦Ĥ
    0.10
    èĥ½åĬĽå¼º
    0.10
    æĺ¯ä»¥
    0.09
    æĢ«
    0.09
    ç«Ļåľ¨
    0.09
    æĪIJçĨŁ
    0.09
    theless
    0.09
    åĥı
    0.09
    å¦ĤæѤ
    0.08
    çݰ代åĮĸ
    0.08
    Activations Density 0.123%

    No Known Activations