© 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. 13738
    Prev
    Next
    INDEX
    Explanations

    enhance, pop, compliments, details, make

    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
    åŀĵ
    -0.25
    为èĩªå·±
    -0.21
    大è§Ħ模
    -0.20
    åı¯éĿł
    -0.20
    isma
    -0.20
    -meta
    -0.19
    èĥ½æ»¡è¶³
    -0.19
    社ä¼ļåĮĸ
    -0.19
    åı£æ°´
    -0.19
    éľĩæĥĬ
    -0.19
    POSITIVE LOGITS
    åİŁæľīçļĦ
    0.23
    uate
    0.20
    åİŁæľī
    0.20
    addColumn
    0.20
    ãĥIJãĥ©ãĥ³ãĤ¹
    0.20
    ä¹ĭç¾İ
    0.20
    æľ¬æĿ¥å°±
    0.20
    对æ¯Ķ
    0.19
    èħ°éĥ¨
    0.19
    çľ¼éĥ¨
    0.19
    Activations Density 0.015%

    No Known Activations