© 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. 15641
    Prev
    Next
    INDEX
    Explanations

    complexes, laboratory, health, display, groupId, John

    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
    opes
    -0.20
    oping
    -0.19
    yh
    -0.18
    çĥ¹
    -0.18
    ä¸įä¸ĭ
    -0.17
    çĨĺ
    -0.17
     Elephant
    -0.17
    ulus
    -0.17
    åħ³éĶ®åŃĹ
    -0.17
    ç¨Ķ
    -0.17
    POSITIVE LOGITS
    è¿Ļ对
    0.25
     Muj
    0.20
    ︿
    0.19
    纵
    0.18
    横
    0.18
    ngo
    0.18
    æĢ»ä½ĵ
    0.18
    getResponse
    0.18
    第äºĮç§į
    0.18
     bp
    0.17
    Activations Density 0.795%

    No Known Activations