© 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. 59447
    Prev
    Next
    INDEX
    Explanations

    assurance or expectation

    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
    æľªç»ıæİĪæĿĥ
    -0.09
    çħ¨
    -0.09
    lest
    -0.09
    èħº
    -0.09
    ents
    -0.09
    çŁ¿çī©è´¨
    -0.09
    agn
    -0.09
    acket
    -0.09
     ineligible
    -0.09
    æĹ¨åľ¨
    -0.08
    POSITIVE LOGITS
    çĽ¸ä¿¡
    0.14
    æĢĢçĸij
    0.12
    认为
    0.11
     believe
    0.11
     believes
    0.10
     bele
    0.10
     doubt
    0.10
     suspicion
    0.09
    è§īå¾Ĺ
    0.09
     belief
    0.09
    Activations Density 0.043%

    No Known Activations