© 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. 12979
    Prev
    Next
    INDEX
    Explanations

    for the purpose of

    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
     altern
    -0.19
    è´²
    -0.18
    ä¸Ģ个éĹ®é¢ĺ
    -0.18
    çĶ¨å¾®ä¿¡
    -0.18
     impro
    -0.18
    Unhandled
    -0.17
    SMTP
    -0.17
    ä¸ĢèĦļ
    -0.17
    ино
    -0.17
    æİī
    -0.17
    POSITIVE LOGITS
    æľªæĿ¥çļĦ
    0.23
    å¸ĤåľºçļĦ
    0.22
    åŃ¦æł¡çļĦ
    0.21
    大ä¼Ĺ
    0.20
     Glad
    0.20
     Constructs
    0.19
    èĢĮæĪIJ
    0.19
    íĸIJ
    0.19
    ä¸Ĭ级
    0.19
    ypad
    0.19
    Activations Density 0.057%

    No Known Activations