© 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. 3164
    Prev
    Next
    INDEX
    Explanations

    next followed by a noun

    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
    amp
    -0.22
    ä¼ļè§ģ
    -0.22
    adox
    -0.22
    uz
    -0.22
    aho
    -0.21
    åĵªåĦ¿
    -0.21
    å½ĵå¹´
    -0.20
    ä¸įæĸŃæī©å¤§
    -0.20
    ä¸ĭåįĬåľº
    -0.20
    å°ıèħ¿
    -0.20
    POSITIVE LOGITS
    -generation
    0.27
    InstanceOf
    0.27
    -ever
    0.27
    -than
    0.27
    -largest
    0.26
     few
    0.25
     incarn
    0.24
    -best
    0.23
    aviest
    0.23
     кÑĢÑĥп
    0.23
    Activations Density 0.015%

    No Known Activations