© 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. 14241
    Prev
    Next
    INDEX
    Explanations

    merger, independence, closing, relocation

    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
    éĥ½æĺ¯éĿŀ常
    -0.20
    æŃ£ãģĹãģĦ
    -0.20
    æŃ£ç¡®
    -0.20
    ASTER
    -0.20
    _ENTRY
    -0.20
    è´¨éĩı管çIJĨ
    -0.19
    æŃ£ç¡®çļĦ
    -0.19
    åħ¨è¿ĩç¨ĭ
    -0.19
    严å¯Ĩ
    -0.19
    淹没
    -0.19
    POSITIVE LOGITS
     or
    0.26
    çļĦåı¯èĥ½æĢ§
    0.26
     possibly
    0.26
    æĪĸèĢħ
    0.26
     perhaps
    0.24
     possible
    0.24
    æĪĸ
    0.24
    ä¸Ģäºĭ
    0.23
    æĪĸ许
    0.23
     somehow
    0.22
    Activations Density 0.094%

    No Known Activations