© 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. 15490
    Prev
    Next
    INDEX
    Explanations

    seasonal periods

    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
    HashCode
    -0.21
    åı«æĪij
    -0.20
    æľĢæĸ°çļĦ
    -0.20
    é¦Ĩ
    -0.19
    åľ¨çĶŁæ´»ä¸Ń
    -0.19
    ç§ijæĬĢåĽŃ
    -0.19
    éĿ©æĸ°
    -0.19
    èĤ¤
    -0.19
    åľ°éģĵ
    -0.19
    亲æīĭ
    -0.18
    POSITIVE LOGITS
    æĹ¶æ®µ
    0.24
    éĢļ常æĺ¯
    0.23
     traditionally
    0.23
    éĺ¶æ®µ
    0.22
    ç¿İ
    0.22
    éĥ½ä¼ļæľī
    0.21
    éĢļ常
    0.21
    alloca
    0.21
     typically
    0.20
    æĥ¯ä¾ĭ
    0.20
    Activations Density 0.039%

    No Known Activations