© 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. 12681
    Prev
    Next
    INDEX
    Explanations

    Default, My, parent, the

    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
    éģĤ
    -0.20
    æľīåĬĽ
    -0.19
    ond
    -0.19
    æݨèįIJéĺħ读
    -0.18
    é«ĺ度
    -0.18
    çĶļèĩ³
    -0.17
     strong
    -0.17
    urally
    -0.17
     ris
    -0.17
     bog
    -0.17
    POSITIVE LOGITS
    -UA
    0.20
    æµĨ
    0.20
    åł´åIJĪãģ«ãģ¯
    0.19
    quarters
    0.19
    å¹´é¾Ħ段
    0.19
    пÑĢÑı
    0.19
    éĤĹ
    0.19
    æݧèĤ¡éĽĨåĽ¢
    0.19
    Scalars
    0.18
    åĨĻåŃĹ楼
    0.18
    Activations Density 0.294%

    No Known Activations