© 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. 3319
    Prev
    Next
    INDEX
    Explanations

    Martin, Jenkins, Roberts, Murray, Heath, Robinson

    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
    å°ı游æĪı
    -0.28
    creenshot
    -0.26
    æľĢåIJİä¸Ģ次
    -0.25
    èµ
    -0.25
    éĶĻè¿ĩ
    -0.23
    ivr
    -0.22
     occured
    -0.22
    æ¶ī
    -0.22
    åĪĨä¼ļ
    -0.22
    æ¶īåıĬ
    -0.21
    POSITIVE LOGITS
    ä¸ºæł¸å¿ĥ
    0.34
    ä¸ºæł¸å¿ĥçļĦ
    0.29
    æĶ¯æĴij
    0.28
     synerg
    0.28
    eland
    0.27
     core
    0.27
    /Core
    0.26
    é¢Ĩè¡Ķ
    0.26
     Core
    0.25
    à¸Ħà¸Ńย
    0.25
    Activations Density 0.032%

    No Known Activations