© 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. 17251
    Prev
    Next
    INDEX
    Explanations

    words ending in ary/ine/osome/ia

    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
    edException
    -0.21
    uding
    -0.19
    åºĨåħ¸
    -0.19
     ìĸ
    -0.18
    åĪ®
    -0.18
    çģ¿çĥĤ
    -0.18
    åĽ½éĺ²
    -0.17
    涣
    -0.17
    kl
    -0.17
    çļĩåĨł
    -0.17
    POSITIVE LOGITS
    ongo
    0.19
    yne
    0.19
    è¤Ĵ
    0.19
    溺
    0.18
    å¼Ĥåľ°
    0.18
    oton
    0.18
     Convenience
    0.18
     Shut
    0.17
    lic
    0.17
    éĵĮ
    0.17
    Activations Density 0.793%

    No Known Activations