© 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. 13637
    Prev
    Next
    INDEX
    Explanations

    go or go home

    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
    æĹ¢æľī
    -0.20
    éĥĬåĮº
    -0.20
    AIM
    -0.19
    ä¸ºçĽ®æłĩ
    -0.19
    åѵåĮĸ
    -0.19
    APS
    -0.18
    ãĤ°ãĥ«
    -0.18
     PARTICULAR
    -0.18
     Urs
    -0.18
    èĵĭ
    -0.18
    POSITIVE LOGITS
     versus
    0.20
    eson
    0.20
    æĶ¾è¿ĩ
    0.20
    è¦ģä¹Ī
    0.20
     infl
    0.20
    对æѤ
    0.20
    好åIJ§
    0.19
    yne
    0.19
    oplay
    0.19
     accept
    0.19
    Activations Density 0.031%

    No Known Activations