© 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. 29708
    Prev
    Next
    INDEX
    Explanations

    allegations, allelic variation

    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
    onical
    -0.10
    apia
    -0.09
    çķĮçļĦ
    -0.09
    å©¿
    -0.09
    åĽŀé¦ĸ
    -0.09
    soever
    -0.09
     latter
    -0.09
    sav
    -0.09
    æĿ¥ä¸´
    -0.09
    Ulus
    -0.09
    POSITIVE LOGITS
    uded
    0.09
     fred
    0.09
    ibel
    0.09
    iance
    0.09
    ry
    0.09
    aire
    0.08
    usion
    0.08
    ready
    0.08
    owing
    0.08
    ance
    0.08
    Activations Density 0.034%

    No Known Activations