© 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. 11609
    Prev
    Next
    INDEX
    Explanations

    US states and cities

    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
    åįļ
    -0.20
    åºIJ
    -0.20
    éĵİ
    -0.20
    翳
    -0.20
    #for
    -0.19
    æĸ½å·¥åįķä½į
    -0.19
    èģ¿
    -0.19
    ewe
    -0.19
    _bo
    -0.19
    ç¿İ
    -0.19
    POSITIVE LOGITS
    åľ¨ç¾İåĽ½
    0.39
    ç¾İåĽ½
    0.39
     US
    0.36
    USA
    0.35
    欧ç¾İ
    0.34
     USA
    0.34
     미êµŃ
    0.32
    ç¾İåľĭ
    0.31
     СШÐIJ
    0.31
    ä¸Ńç¾İ
    0.31
    Activations Density 0.596%

    No Known Activations