© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15934
    Prev
    Next
    INDEX
    Explanations

    city names endings

    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
    Not in Any Lists

    No Comments

    Negative Logits
    éĥ´
    -0.23
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    -0.19
    lete
    -0.19
     repl
    -0.19
    antee
    -0.18
    ctest
    -0.18
    -European
    -0.18
    缴åįĩ
    -0.17
    ä¸ªåĽ½å®¶
    -0.17
     Smarty
    -0.17
    POSITIVE LOGITS
    çļĦ大
    0.20
    åĸ»
    0.19
    erin
    0.18
    çŃīåľ°
    0.18
     représ
    0.18
    å¿ĥ头
    0.18
     Richie
    0.17
    æķijæ²»
    0.17
     baker
    0.17
    åĪĿ级
    0.17
    Activations Density 0.198%

    No Known Activations