© 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. 16395
    Prev
    Next
    INDEX
    Explanations

    comic artists and writers

    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
    å°±é¤IJ
    -0.23
    çIJµ
    -0.20
     reim
    -0.20
    éĢĨåĬ¿
    -0.19
    ä¸įå±ŀäºİ
    -0.19
    ctx
    -0.19
    =context
    -0.19
     Pf
    -0.18
    èĥĻ
    -0.18
    оде
    -0.18
    POSITIVE LOGITS
    anning
    0.21
    ibil
    0.21
    istar
    0.20
    è¾īçħĮ
    0.20
    详
    0.19
    楷
    0.19
    ç´łæĿIJ
    0.19
    å¥İ
    0.19
    IBC
    0.19
    ç¼ĸåĨĻ
    0.19
    Activations Density 0.012%

    No Known Activations