© 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. 26103
    Prev
    Next
    INDEX
    Explanations

    the followed by nouns

    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
    AAP
    -0.10
     Shea
    -0.10
    .Apis
    -0.09
    akte
    -0.09
    AME
    -0.09
    ichever
    -0.09
    uco
    -0.09
    гаÑĢ
    -0.09
    otten
    -0.09
    /libs
    -0.08
    POSITIVE LOGITS
     Adventures
    0.09
    ignment
    0.09
    éļIJ约
    0.08
    æĭ¿äºĨ
    0.08
    对æĸ¹
    0.08
    inerary
    0.08
    ä¸įä¿¡
    0.08
    ographs
    0.08
    ãĤĴ缮
    0.07
    snd
    0.07
    Activations Density 0.308%

    No Known Activations