© 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. 10716
    Prev
    Next
    INDEX
    Explanations

    new or newly introduced

    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
    æĻļå¹´
    -0.22
    æ®ĭ
    -0.20
    нев
    -0.20
    羡
    -0.20
    å¾Ĺ罪
    -0.20
    èĽ¤
    -0.19
    åŃIJåŃĻ
    -0.19
    类似çļĦ
    -0.18
    俱
    -0.18
    楸
    -0.18
    POSITIVE LOGITS
    éĿ¢åŃĶ
    0.28
    åħ¥
    0.28
    è¿ĽæĿ¥
    0.27
    人éĢī
    0.23
    åĬłåħ¥
    0.21
    åħ¥åľº
    0.21
    åħ¥èģĮ
    0.21
    rac
    0.21
    ä¸Ĭå²Ĺ
    0.20
    â¼Ĭ
    0.20
    Activations Density 0.031%

    No Known Activations