© 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. 12543
    Prev
    Next
    INDEX
    Explanations

    sun sights, flare, notice of, [corporate

    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
     Broken
    -0.24
    uran
    -0.23
    OLON
    -0.21
    Broken
    -0.20
    orough
    -0.20
    piry
    -0.19
    ä¸Ģè´¯
    -0.19
    PropertyParams
    -0.18
    cheme
    -0.18
    鸩
    -0.18
    POSITIVE LOGITS
    è¿ijæĹ¥
    0.26
    å¤§åĽ½
    0.23
    é¢ĦèѦ
    0.23
    é¢Ħæµĭ
    0.23
    é¢ĦæĬ¥
    0.22
    è£ħå¤ĩåĪ¶éĢł
    0.21
    طا
    0.20
    ffective
    0.20
    oons
    0.20
    Io
    0.20
    Activations Density 0.009%

    No Known Activations