© 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. 15956
    Prev
    Next
    INDEX
    Explanations

    record

    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
    们éĥ½
    -0.20
    è¶Ĭ大
    -0.20
     Orders
    -0.20
    åħ·æľīä¸Ģå®ļ
    -0.19
     Sized
    -0.18
    æĹ©å°±
    -0.18
    emma
    -0.18
    æľīåºı
    -0.18
    è´µ
    -0.18
    æµ´
    -0.18
    POSITIVE LOGITS
    èī¯å¥½çļĦ
    0.25
    ä¼ĺèī¯
    0.23
    æ¯ĵ
    0.20
    äºĶå¹´
    0.19
    èł
    0.18
     ATK
    0.18
     rating
    0.18
    éĥĩ
    0.18
    èī¯å¥½
    0.18
    è¾ĥ好çļĦ
    0.17
    Activations Density 0.005%

    No Known Activations