© 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. 10569
    Prev
    Next
    INDEX
    Explanations

    recommendation or choice award

    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
    SCAN
    -0.20
    åĬ¡å·¥
    -0.19
     Peach
    -0.19
    åĪĿæģĭ
    -0.19
    WG
    -0.18
     Relationship
    -0.18
    æĶ¹éĿ©åıijå±ķ
    -0.18
    isz
    -0.18
    iface
    -0.18
     FVector
    -0.17
    POSITIVE LOGITS
    æݨèįIJ
    0.32
     recommendation
    0.30
     recommendations
    0.30
    recommend
    0.28
     recomend
    0.26
     recommend
    0.25
     recommended
    0.23
     Recommended
    0.23
    Recommend
    0.23
    recommended
    0.23
    Activations Density 0.010%

    No Known Activations