© 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. 15834
    Prev
    Next
    INDEX
    Explanations

    aiming, shot, target, miss

    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
    åĸĺ
    -0.21
    holm
    -0.21
    ä¸įå®Į
    -0.20
    æĥĺ
    -0.20
    é£İåIJ¹
    -0.20
    apot
    -0.19
    æ¸ħæĸ°
    -0.19
    æĹłç©·
    -0.19
    åįĬ天
    -0.18
    æ·¡æ°´
    -0.18
    POSITIVE LOGITS
    åij½ä¸Ń
    0.36
    缮æłĩ
    0.34
    éĿ¶
    0.34
    ç²¾åĩĨ
    0.31
    精度
    0.31
    åĩĨç¡®æĢ§
    0.30
    target
    0.30
     target
    0.29
    çŀĦåĩĨ
    0.29
    精确
    0.29
    Activations Density 0.026%

    No Known Activations