© 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. 16243
    Prev
    Next
    INDEX
    Explanations

    json keys, structure

    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
    yn
    -0.20
    .removeListener
    -0.18
    o
    -0.18
    cock
    -0.18
     Kin
    -0.18
    merce
    -0.18
    lien
    -0.18
    \<^
    -0.17
     a
    -0.17
    -border
    -0.17
    POSITIVE LOGITS
    æľĢåħ³éĶ®çļĦ
    0.23
    ä¼ĺèī¯
    0.21
    æľ¬åĽ½
    0.21
    使çĶ¨çļĦ
    0.20
    Dimensions
    0.20
    åı¯ä¾Ľ
    0.20
    主è¦ģä»İäºĭ
    0.20
    ä¸ĢåĪĩéĥ½
    0.20
    åºĶä»ĺ
    0.20
    æĽ¾ä»»
    0.20
    Activations Density 0.160%

    No Known Activations