© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12402
    Prev
    Next
    INDEX
    Explanations

    bench press exercise

    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
    综åIJĪæĢ§
    -0.21
    iker
    -0.20
    å¦Ĥä½ķåİ»
    -0.19
     somehow
    -0.19
    croft
    -0.18
    ooks
    -0.18
    CLE
    -0.18
    ogen
    -0.18
    hands
    -0.18
    oly
    -0.17
    POSITIVE LOGITS
    次æķ°
    0.25
     Ñĩелов
    0.19
    åIJĦæł·
    0.19
    é¢Ĩä¼ļ
    0.18
    ÑĢин
    0.18
    åİĿ
    0.18
    гÑĢаниÑĩ
    0.18
    éĩijéĻµ
    0.18
    qua
    0.17
    æĬļ
    0.17
    Activations Density 0.005%

    No Known Activations