© 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. 29661
    Prev
    Next
    INDEX
    Explanations

    forgiveness and forgiving

    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
    æĪª
    -0.09
    éĺī
    -0.08
    æŁ¥å°ģ
    -0.08
    主页
    -0.08
     Lair
    -0.08
    åĽ°æī°
    -0.08
    çĤľ
    -0.08
    mue
    -0.08
    lut
    -0.08
    缩
    -0.08
    POSITIVE LOGITS
    åİŁè°ħ
    0.27
    宽容
    0.26
    容å¿į
    0.25
    è°ħ解
    0.22
     forgiving
    0.21
    åĮħ容
    0.21
     forgive
    0.20
     forgiven
    0.20
     forgiveness
    0.18
    åħģ许
    0.18
    Activations Density 0.082%

    No Known Activations