© 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. 60585
    Prev
    Next
    INDEX
    Explanations

    intense adjectives followed by situations or outcomes

    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
    ç½ijçĤ¹
    -0.08
    çĶŁåij½çļĦ
    -0.08
    çĶŁåij½
    -0.08
    벤
    -0.08
    alloca
    -0.08
    åĢ¾æĸľ
    -0.08
    ozilla
    -0.08
    unders
    -0.08
    alar
    -0.08
    iliar
    -0.08
    POSITIVE LOGITS
    ingly
    0.14
    åµĺ
    0.10
    èĢĮåĩº
    0.10
    ly
    0.10
    inct
    0.09
    ãĤ«ãĥ³
    0.09
    antly
    0.09
     lyon
    0.09
    æīĪ
    0.09
    kest
    0.09
    Activations Density 0.027%

    No Known Activations