© 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. 17292
    Prev
    Next
    INDEX
    Explanations

    producer, director, actor, photographer

    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
     lob
    -0.23
    fol
    -0.22
    ä¸Ģ身
    -0.21
    lob
    -0.20
    VIP
    -0.19
     Rudd
    -0.19
    è£ħå¤ĩåĪ¶éĢł
    -0.18
    ä¹ħ
    -0.18
     fur
    -0.18
    ä¼´éļı
    -0.18
    POSITIVE LOGITS
    对èĩªå·±
    0.24
    èĩªè¡Į
    0.23
     himself
    0.23
    eln
    0.22
    积æŀģåıĤä¸İ
    0.21
    èĩªåįij
    0.21
    ä»ĸèĩªå·±
    0.21
    slash
    0.21
    亲èĩª
    0.21
    ç³Ł
    0.20
    Activations Density 0.287%

    No Known Activations