© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17205
    Prev
    Next
    INDEX
    Explanations

    relational calculus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    âĬĭ
    -0.22
    åŀĤ缴
    -0.22
     eskort
    -0.22
    æĬ±åĽ¢
    -0.22
    ToPoint
    -0.21
    pyx
    -0.21
     salopes
    -0.21
    âĨ£
    -0.21
    å¿«éĢŁ
    -0.20
    çĶ¨å·¥
    -0.20
    POSITIVE LOGITS
     redes
    0.25
     qua
    0.24
     (
    0.23
     causal
    0.23
     relativ
    0.22
    ä¹ĭæīĢ以
    0.22
     bald
    0.22
     abbrev
    0.21
    é³ĥ
    0.21
    ascript
    0.20
    Activations Density 0.107%

    No Known Activations