© 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. 13690
    Prev
    Next
    INDEX
    Explanations

    leave no trace

    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
    éŸ
    -0.23
    æĮ¡
    -0.21
    edom
    -0.21
    å¥ĩèij©
    -0.20
    çĿ£
    -0.20
    æİĴæĸ¥
    -0.20
    赶æĿ¥
    -0.19
    èĭŁ
    -0.19
    è´±
    -0.19
    _watch
    -0.19
    POSITIVE LOGITS
    çķĻä¸ĭ
    0.48
    çķĻä¸ĭäºĨ
    0.40
    éģĹçķĻ
    0.36
    çĹķ迹
    0.32
     leaving
    0.31
    çķĻ
    0.31
    ä¸įçķĻ
    0.31
    Leave
    0.29
    çķĻç»Ļ
    0.29
     footprint
    0.28
    Activations Density 0.138%

    No Known Activations