© 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. 12679
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åĮ¡
    -0.20
    è°ij
    -0.20
    urname
    -0.19
    åİĨæĿ¥
    -0.18
    ivant
    -0.18
    æīĭä¸ĭ
    -0.18
    çłĶ究éĻ¢
    -0.18
    ä½Ĩä»ĸ们
    -0.18
    ðŁĵ·
    -0.18
    æ¹¾
    -0.18
    POSITIVE LOGITS
    emp
    0.21
    ç©¿
    0.21
    ä¸Ńå¤ĸ
    0.19
    姨
    0.18
    elp
    0.18
    arbon
    0.18
    æģŃåĸľ
    0.18
     aft
    0.18
    egrity
    0.17
    åĵŃ
    0.17
    Activations Density 0.000%

    No Known Activations