© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 13631
    Prev
    Next
    INDEX
    Explanations

    court case file numbers

    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
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.19
    acey
    -0.19
    大æ´ĭ
    -0.19
    à¸Ĥà¸Ļา
    -0.19
    主è¦ģ
    -0.19
    à¸Ħà¸ĵะà¸ģรรม
    -0.18
    agnar
    -0.18
     моÑīн
    -0.18
    оÑī
    -0.18
    à¸Ńำà¸Ļวยà¸Ħวาม
    -0.18
    POSITIVE LOGITS
    çĮ¾
    0.22
    éı¡
    0.20
    åģİ
    0.19
    éĩijèŀįå᱿ľº
    0.19
    æIJºç¨ĭ
    0.18
    дов
    0.18
     nim
    0.17
    交æį¢
    0.17
     facebook
    0.17
    _NUMERIC
    0.17
    Activations Density 0.099%

    No Known Activations