© 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. 14762
    Prev
    Next
    INDEX
    Explanations

    ATP Tour, critical care, data center, copying machines

    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
    éģij
    -0.20
     Sanct
    -0.20
    obel
    -0.18
    æĿ¾å¼Ľ
    -0.18
    èĥ¡åIJĮ
    -0.17
     BUG
    -0.17
    legg
    -0.17
    裸
    -0.17
    è°·æŃĮ
    -0.17
    èĥ¶åĽĬ
    -0.17
    POSITIVE LOGITS
    åķĨæĬ¥
    0.20
    ansi
    0.20
    ä¸įæĩĤ
    0.19
    ä¸Ĭ涨
    0.19
    æ©Ħ
    0.18
     actual
    0.18
    alloc
    0.17
    ãħ¤
    0.17
    èĽIJ
    0.17
    ipt
    0.17
    Activations Density 1.046%

    No Known Activations