© 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. 10492
    Prev
    Next
    INDEX
    Explanations

    first to access

    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
    èĩªçIJĨ
    -0.21
    ifs
    -0.20
    åĬ©ãģij
    -0.20
    åĪĿè¡·
    -0.20
    黼
    -0.19
    踬
    -0.19
    å¸ĮæľĽèĥ½å¤Ł
    -0.18
    ullo
    -0.18
     assort
    -0.18
    æļĤåģľ
    -0.18
    POSITIVE LOGITS
    ä¸ĵ享
    0.22
    åĨħå¹ķ
    0.22
    访éĹ®
    0.21
     privat
    0.21
     access
    0.21
    /private
    0.20
    çĭ¬å®¶
    0.20
    çĶ³
    0.20
    apper
    0.20
    Access
    0.20
    Activations Density 0.017%

    No Known Activations