© 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. 15572
    Prev
    Next
    INDEX
    Explanations

    analysis, premium, depreciation, volume, capitalization

    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
    让åѦçĶŁ
    -0.22
    è§ģè¯Ĩ
    -0.21
    Indent
    -0.21
    æĶ¾æīĭ
    -0.21
     daring
    -0.19
    mj
    -0.18
    REP
    -0.18
    rud
    -0.18
    èĥİ
    -0.18
    åŁ
    -0.18
    POSITIVE LOGITS
    软
    0.19
    ä¹IJéĺŁ
    0.18
    remium
    0.18
    ä¼łç»Łäº§ä¸ļ
    0.18
    ubar
    0.18
    imore
    0.18
    _removed
    0.18
    замен
    0.17
    ynet
    0.17
    iesel
    0.17
    Activations Density 0.002%

    No Known Activations