© 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. 6113
    Prev
    Next
    INDEX
    Explanations

    .com / 's / . / generated

    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
    ordo
    -0.10
    æŃ¥åħ¥
    -0.10
    æĤ¸
    -0.09
    [of
    -0.09
    çĿ¦
    -0.09
    Wik
    -0.08
    èĢĮæĪIJ
    -0.08
    ief
    -0.08
    seat
    -0.08
    çĮ
    -0.08
    POSITIVE LOGITS
    æ²±
    0.09
    ç²ī
    0.08
    sla
    0.08
    itage
    0.08
    æģ³
    0.08
    pps
    0.08
    ukes
    0.08
    lator
    0.08
    ipse
    0.08
    ä½ľæģ¯
    0.08
    Activations Density 0.001%

    No Known Activations