© 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. 3215
    Prev
    Next
    INDEX
    Explanations

    couch, pouch, sofa

    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
    æīĭæĮģ
    -0.24
     sik
    -0.22
    è£ħç½®
    -0.20
    ksen
    -0.19
    ceptive
    -0.19
    社ä¼ļ
    -0.19
     orthodox
    -0.19
    nable
    -0.19
    cycl
    -0.19
     bow
    -0.18
    POSITIVE LOGITS
    (es
    0.29
    rooms
    0.26
    ä¸ĬçļĦ
    0.25
    åīįæīĢ
    0.24
    æĮģæľī人
    0.23
    ernet
    0.23
    inator
    0.23
    iest
    0.23
    agne
    0.22
    ä¸Ĭæľī
    0.22
    Activations Density 0.004%

    No Known Activations