© 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. 10412
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun/colon

    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
    èµļéĴ±
    -0.21
    rum
    -0.20
    楣
    -0.20
    åı¯ä»¥èİ·å¾Ĺ
    -0.20
    åĩºèº«
    -0.19
     pros
    -0.19
     born
    -0.18
    èij³
    -0.18
     scouting
    -0.18
    并éĿŀ
    -0.18
    POSITIVE LOGITS
    ç´§æİ¥çĿĢ
    0.25
    åĨįåĪ°
    0.22
    æİ¥çĿĢ
    0.22
     заÑĤем
    0.21
    çĦ¶åIJİ
    0.21
    éļıåį³
    0.20
    éļıåIJİ
    0.20
    èĨł
    0.20
    okers
    0.20
    åĬ¨çĶ»
    0.20
    Activations Density 0.013%

    No Known Activations