© 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. 12072
    Prev
    Next
    INDEX
    Explanations

    antibody screening and library hybridization

    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
    inion
    -0.23
    ÑĤик
    -0.21
     mainstream
    -0.19
    è·ijåİ»
    -0.19
    enos
    -0.19
     Stam
    -0.18
    æĤª
    -0.18
    ancock
    -0.18
    cip
    -0.17
    åľ¨çݩ家ä¸Ń
    -0.17
    POSITIVE LOGITS
    çľł
    0.22
    æ»ļ
    0.21
    eya
    0.20
    åıijçİ°äºĨ
    0.20
    Ñİ
    0.20
    æĬķèµĦåŁºéĩij
    0.19
    大海
    0.19
    æ·¡
    0.19
    å¯Į
    0.19
    æ³ķåĪ¶
    0.19
    Activations Density 0.433%

    No Known Activations