© 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. 26019
    Prev
    Next
    INDEX
    Explanations

    wall or walled

    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
    iated
    -0.10
    pery
    -0.10
    ially
    -0.10
    iating
    -0.10
    åºľ
    -0.10
    yled
    -0.09
    æĺ´
    -0.09
    lei
    -0.09
    iator
    -0.09
    èij±
    -0.09
    POSITIVE LOGITS
    papers
    0.11
    entin
    0.09
    paper
    0.09
    outh
    0.09
    áºŃn
    0.09
    å¾Ĺä½ı
    0.09
    ows
    0.09
    ä»ŀ
    0.09
    abies
    0.08
    owed
    0.08
    Activations Density 0.035%

    No Known Activations