© 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. 3359
    Prev
    Next
    INDEX
    Explanations

    congressional committees

    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
    å¾Ĺ天
    -0.27
    ersistence
    -0.24
    ä¸Ģçĵ¶
    -0.23
     гаÑĢан
    -0.23
    ERSIST
    -0.23
     Voll
    -0.22
    èıľèĤ´
    -0.22
    好æĦŁ
    -0.22
    Ľå»º
    -0.22
    ersistent
    -0.21
    POSITIVE LOGITS
     committee
    0.34
    å§Ķåijĺä¼ļ
    0.29
     committees
    0.28
    çĶŁæ®ĸ
    0.27
    å§Ķåijĺ
    0.27
     Committee
    0.26
    éĴ³
    0.25
     last
    0.24
     Committees
    0.24
     Sect
    0.24
    Activations Density 0.005%

    No Known Activations