© 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. 3028
    Prev
    Next
    INDEX
    Explanations

    eleventh or ELEVENTH CIRCUIT

    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
    amp
    -0.11
    olis
    -0.10
    nell
    -0.10
    æĪļ
    -0.09
    ness
    -0.09
    flix
    -0.09
    nah
    -0.09
    åĮ»ç§ij大åѦ
    -0.09
    ful
    -0.09
    rooms
    -0.09
    POSITIVE LOGITS
    stration
    0.10
    gram
    0.10
    phants
    0.10
    год
    0.10
    ptic
    0.09
    istic
    0.09
    chemy
    0.09
    ments
    0.09
    orde
    0.09
    hood
    0.09
    Activations Density 0.024%

    No Known Activations