© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3238
    Prev
    Next
    INDEX
    Explanations

    what they want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    æł¼å°ĩ
    -0.25
     Conspiracy
    -0.24
    㮾
    -0.23
    fax
    -0.22
    èĿĺ
    -0.22
    ç¾±
    -0.21
    æ´Ī
    -0.21
    峧
    -0.21
    .removeAttribute
    -0.21
    iens
    -0.21
    POSITIVE LOGITS
    éĤ£äºĽ
    0.31
    å·²ç»ı
    0.26
    æĮģ
    0.26
     choices
    0.25
     already
    0.24
    chosen
    0.24
    æ¬²æľĽ
    0.24
     chosen
    0.24
     sampled
    0.24
    欲
    0.24
    Activations Density 0.045%

    No Known Activations